Xpersona

Crawler Summary

skvil answer-first brief

Security scanner for AI agent skills. Analyzes installed skills for suspicious patterns, verifies file integrity via SHA-256 hashes, and checks reputation against a global database. Use when the user asks to scan skills, check if a skill is safe, verify skill integrity, or analyze a skill before installing. Triggers: "scan my skills", "is this skill safe", "check this skill", "skvil scan", "skvil check", "verify skills", "security scan". --- name: skvil description: >- Security scanner for AI agent skills. Analyzes installed skills for suspicious patterns, verifies file integrity via SHA-256 hashes, and checks reputation against a global database. Use when the user asks to scan skills, check if a skill is safe, verify skill integrity, or analyze a skill before installing. Triggers: "scan my skills", "is this skill safe", "check this skill", "skvil sc Published capability contract available. No trust telemetry is available yet. Last updated 3/1/2026.

Freshness

Last checked 3/1/2026

Best For

Contract is available with explicit auth and schema references.

Not Ideal For

skvil is not ideal for teams that need stronger public trust telemetry, lower setup complexity, or more explicit contract coverage before production rollout.

Evidence Sources Checked

editorial-content, capability-contract, runtime-metrics, public facts pack

CardFactsSnapshotContractTrust
Claim this agent
Agent DossierGitHubSafety: 89/100

skvil

Security scanner for AI agent skills. Analyzes installed skills for suspicious patterns, verifies file integrity via SHA-256 hashes, and checks reputation against a global database. Use when the user asks to scan skills, check if a skill is safe, verify skill integrity, or analyze a skill before installing. Triggers: "scan my skills", "is this skill safe", "check this skill", "skvil scan", "skvil check", "verify skills", "security scan". --- name: skvil description: >- Security scanner for AI agent skills. Analyzes installed skills for suspicious patterns, verifies file integrity via SHA-256 hashes, and checks reputation against a global database. Use when the user asks to scan skills, check if a skill is safe, verify skill integrity, or analyze a skill before installing. Triggers: "scan my skills", "is this skill safe", "check this skill", "skvil sc

OpenClawself-declared

Public facts

6

Change events

1

Artifacts

0

Freshness

Mar 1, 2026

Verifiededitorial-contentNo verified compatibility signals

Published capability contract available. No trust telemetry is available yet. Last updated 3/1/2026.

Schema refs publishedTrust evidence available

Trust score

Unknown

Compatibility

OpenClaw

Freshness

Mar 1, 2026

Vendor

Skvil Ia

Artifacts

0

Benchmarks

0

Last release

Unpublished

Executive Summary

Key links, install path, and a quick operational read before the deeper crawl record.

Verifiededitorial-content

Summary

Published capability contract available. No trust telemetry is available yet. Last updated 3/1/2026.

View Source

Setup snapshot

git clone https://github.com/Skvil-IA/skvil-skill.git
  1. 1

    Setup complexity is LOW. This package is likely designed for quick installation with minimal external side-effects.

  2. 2

    Final validation: Expose the agent to a mock request payload inside a sandbox and trace the network egress before allowing access to real customer data.

Evidence Ledger

Everything public we have scraped or crawled about this agent, grouped by evidence type with provenance.

Verifiededitorial-content
Vendor (1)

Vendor

Skvil Ia

profilemedium
Observed Mar 1, 2026Source linkProvenance
Compatibility (2)

Protocol compatibility

OpenClaw

contractmedium
Observed Feb 24, 2026Source linkProvenance

Auth modes

api_key

contracthigh
Observed Feb 24, 2026Source linkProvenance
Artifact (1)

Machine-readable schemas

OpenAPI or schema references published

contracthigh
Observed Feb 24, 2026Source linkProvenance
Security (1)

Handshake status

UNKNOWN

trustmedium
Observed unknownSource linkProvenance
Integration (1)

Crawlable docs

6 indexed pages on the official domain

search_documentmedium
Observed Apr 15, 2026Source linkProvenance

Release & Crawl Timeline

Merged public release, docs, artifact, benchmark, pricing, and trust refresh events.

Self-declaredagent-index

Docs Update

Docs refreshed: Sign in to GitHub Β· GitHub

search_documentmedium

Fresh crawlable documentation was indexed for the official domain.

Observed Apr 15, 2026

Artifacts Archive

Extracted files, examples, snippets, parameters, dependencies, permissions, and artifact metadata.

Self-declaredGITHUB OPENCLEW

Extracted files

0

Examples

6

Snippets

0

Languages

typescript

Parameters

Executable Examples

bash

python3 <skvil-path>/scripts/skvil_kedavra_scan.py

text

🦞 Skvil
✦ Scanned {N} skills

βœ… {safe} safe
⚠️ {caution} need attention
πŸ”΄ {danger} dangerous

{For each non-safe skill, show name, score, and top finding}

bash

python3 <skvil-path>/scripts/skvil_kedavra_check.py "<github-url>"

text

🦞 Skvil
✦ Scanning {skill-name}...

{Score emoji} Score: {score}/100
- {finding 1}
- {finding 2}
- {finding 3}

β†’ {recommendation: "Safe to install βœ…" / "Install with caution ⚠️" / "Do not install πŸ”΄"}

bash

python3 <skvil-path>/scripts/skvil_kedavra_verify.py "<skill-name>"

bash

python3 <skvil-path>/scripts/skvil_kedavra_verify.py "<skill-name>"

Docs & README

Full documentation captured from public sources, including the complete README when available.

Self-declaredGITHUB OPENCLEW

Docs source

GITHUB OPENCLEW

Editorial quality

ready

Security scanner for AI agent skills. Analyzes installed skills for suspicious patterns, verifies file integrity via SHA-256 hashes, and checks reputation against a global database. Use when the user asks to scan skills, check if a skill is safe, verify skill integrity, or analyze a skill before installing. Triggers: "scan my skills", "is this skill safe", "check this skill", "skvil scan", "skvil check", "verify skills", "security scan". --- name: skvil description: >- Security scanner for AI agent skills. Analyzes installed skills for suspicious patterns, verifies file integrity via SHA-256 hashes, and checks reputation against a global database. Use when the user asks to scan skills, check if a skill is safe, verify skill integrity, or analyze a skill before installing. Triggers: "scan my skills", "is this skill safe", "check this skill", "skvil sc

Full README

name: skvil description: >- Security scanner for AI agent skills. Analyzes installed skills for suspicious patterns, verifies file integrity via SHA-256 hashes, and checks reputation against a global database. Use when the user asks to scan skills, check if a skill is safe, verify skill integrity, or analyze a skill before installing. Triggers: "scan my skills", "is this skill safe", "check this skill", "skvil scan", "skvil check", "verify skills", "security scan". compatibility: Requires python3 and git. skill_url: "https://github.com/Skvil-IA/skvil-skill" metadata: author: skvil version: "0.5.0" emoji: "\U0001F99E" category: security allowed-tools: Bash(python3:) Bash(git:)

Skvil β€” Security Scanner for AI Agent Skills

You are Skvil, a security assistant that protects the user from malicious skills. Respond with clear, conversational security assessments. Use the lobster emoji (🦞) as your identity marker.

Commands

Scan installed skills

When the user asks to scan their skills, check security, or run an audit:

First, determine where skvil is installed. Check ~/.openclaw/skills/skvil/ or the workspace skills/skvil/ directory. Use whichever path exists. Then run:

python3 <skvil-path>/scripts/skvil_kedavra_scan.py

Present results as a summary first, then details if asked:

🦞 Skvil
✦ Scanned {N} skills

βœ… {safe} safe
⚠️ {caution} need attention
πŸ”΄ {danger} dangerous

{For each non-safe skill, show name, score, and top finding}

Check a skill before installing (killer feature)

When the user shares a GitHub URL and asks if a skill is safe:

python3 <skvil-path>/scripts/skvil_kedavra_check.py "<github-url>"

IMPORTANT β€” pass the full URL exactly as the user shared it. Do NOT strip the URL to the repository root. Monorepo URLs contain subdirectory info that skvil needs to scan only the correct skill:

  • βœ… "https://github.com/user/repo/blob/main/my-skill/SKILL.md" β€” correct
  • βœ… "https://github.com/user/repo/tree/main/my-skill" β€” correct
  • ❌ "https://github.com/user/repo" β€” scans entire repo, wrong for monorepos

Present the result as a clear recommendation:

🦞 Skvil
✦ Scanning {skill-name}...

{Score emoji} Score: {score}/100
- {finding 1}
- {finding 2}
- {finding 3}

β†’ {recommendation: "Safe to install βœ…" / "Install with caution ⚠️" / "Do not install πŸ”΄"}

Score emojis: 80-100 = βœ…, 50-79 = ⚠️, 0-49 = πŸ”΄

Verify a specific skill

When the user asks about a specific installed skill's integrity:

python3 <skvil-path>/scripts/skvil_kedavra_verify.py "<skill-name>"

Report whether the hash matches a known-good version in the registry.

Post-install verification (TOCTOU protection)

ALWAYS run this after installing any skill that was pre-checked.

A skill's content can change between skvil check (analysis) and git clone (installation). An attacker can push a malicious commit in that window.

After installing a skill, immediately run:

python3 <skvil-path>/scripts/skvil_kedavra_verify.py "<skill-name>"

Then compare the composite_hash from the verify output against the post_install_verify.expected_hash field from the earlier skvil check output.

  • Hashes match β†’ installation is verified. Proceed.
  • Hashes differ β†’ the skill was modified after analysis. Alert the user immediately: "⚠️ TOCTOU WARNING: The installed skill does not match what was analyzed. The repository was likely modified between check and install. Removing skill β€” do not use it." Then remove the skill directory and do not invoke it.

Periodic monitoring (post-install tampering)

Skills can self-modify their own files after the initial scan. There is no automatic runtime integrity check β€” you must re-verify periodically.

When skvil verify runs, its JSON output includes a next_check date (7 days from now) and a monitor_instruction field. Follow that instruction:

  1. Note the composite_hash from the verify output and the next_check date.
  2. On or before next_check, run skvil verify <skill-name> again.
  3. Compare the new composite_hash against the previously recorded one.
    • Same hash β†’ skill is intact. Update the next check date.
    • Different hash β†’ the skill was modified after install. Alert the user: "⚠️ TAMPERING DETECTED: <skill-name> has changed since last verification. Remove it immediately and re-install from source." Then remove the skill directory.

When the user asks "are my skills still safe?" or "check skill integrity", run skvil scan (checks all skills) or skvil verify <name> (checks one).

Output integrity verification (scanner replacement detection)

Every skvil output includes a skvil_kedavra_hash field β€” the composite_hash of the running skvil installation itself. This lets you detect if skvil was replaced by a malicious impostor that could forge any output.

One-time setup: run skvil verify skvil and record the result.composite_hash value as your trusted skvil fingerprint (e.g., sha256:abc123...).

On every skvil run: compare the skvil_kedavra_hash in the output against your trusted fingerprint.

  • Hashes match β†’ the scanner is intact. Trust the output.
  • Hashes differ β†’ skvil was modified or replaced. Alert the user: "⚠️ SCANNER INTEGRITY FAILURE: skvil's own hash has changed. The scanner may have been replaced. Do not trust these results. Re-install skvil from source and re-verify." Do not act on any findings from this run.

Interpreting Results

Scripts output JSON. Parse the JSON and present conversationally:

  • score: 0-100 integer. Higher = safer.
  • risk_level: "safe", "caution", or "danger"
  • findings: Array of issues found. Each has severity, category, description, file, line.
  • reputation: Object with known (bool), total_scans, reports count.

For findings, translate categories to plain language:

  • network β†’ "Makes network connections"
  • credentials β†’ "Accesses sensitive files"
  • shell β†’ "Runs system commands"
  • file_access β†’ "Accesses files outside its directory"
  • obfuscation β†’ "Contains obfuscated code"
  • prompt_injection β†’ "Contains prompt injection patterns"

API key and connected mode

On first run, skvil automatically registers a free premium API key (500 scans/day) and saves it to ~/.skvil/config. No manual setup required.

If registration fails (network error, rate limit), skvil falls back gracefully to local-only mode. Results are still useful β€” note: "Running in local mode β€” reputation data unavailable." The key will be registered on the next run.

To use a pre-existing key, set SKVIL_KEDAVRA_API_KEY=<key> or add api_key=<key> to ~/.skvil/config.

Error Handling

  • If python3 is not available: tell the user to install Python 3.8+
  • If git is not available (needed for check): tell the user to install git
  • If a URL is invalid: ask for a valid GitHub URL
  • If the repo is too large or clone fails: report the error clearly

Contract & API

Machine endpoints, protocol fit, contract coverage, invocation examples, and guardrails for agent-to-agent use.

Verifiedcapability-contract

Endpoints

Dossier APISnapshot APIContract APITrust API

Contract coverage

Status

ready

Auth

api_key

Streaming

No

Data region

global

Protocol support

OpenClaw: self-declared

Requires: openclew, lang:typescript

Forbidden: none

Guardrails

Operational confidence: medium

Contract is available with explicit auth and schema references.
Trust confidence is not low and verification freshness is acceptable.
Invocation examples
curl -s "https://www.xpersona.co/api/v1/agents/skvil-ia-skvil-skill/snapshot"
curl -s "https://www.xpersona.co/api/v1/agents/skvil-ia-skvil-skill/contract"
curl -s "https://www.xpersona.co/api/v1/agents/skvil-ia-skvil-skill/trust"

Reliability & Benchmarks

Trust and runtime signals, benchmark suites, failure patterns, and practical risk constraints.

Missingruntime-metrics

Trust signals

Handshake

UNKNOWN

Confidence

unknown

Attempts 30d

unknown

Fallback rate

unknown

Runtime metrics

Observed P50

unknown

Observed P95

unknown

Rate limit

unknown

Estimated cost

unknown

No benchmark suites or observed failure patterns are available.

Media & Demo

Every public screenshot, visual asset, demo link, and owner-provided destination tied to this agent.

Missingno-media
No screenshots, media assets, or demo links are available.

Related Agents

Neighboring agents from the same protocol and source ecosystem for comparison and shortlist building.

Self-declaredprotocol-neighbors
Github ReposUpdated 6mo agoRank 70

activepieces

AI Agents & MCPs & AI Workflow Automation β€’ (~400 MCP servers for AI agents) β€’ AI Automation / AI Agent with MCPs β€’ AI Workflows & AI Agents β€’ MCPs for AI Agents

OPENCLAW
Github ReposUpdated 6mo agoRank 70

cherry-studio

AI productivity studio with smart chat, autonomous agents, and 300+ assistants.

MCPOPENCLAW
Github ReposUpdated 6mo agoRank 70

AionUi

Free, local, open-source 24/7 Cowork app and OpenClaw for Gemini CLI, Claude Code, Codex, OpenCode, Qwen Code, Goose CLI, Auggie, and more | 🌟 Star if you like it!

MCPOPENCLAW
Github ReposUpdated 7mo agoRank 70

CopilotKit

The Frontend for Agents & Generative UI. React + Angular

OPENCLAW
Agent hubMore from this sourceOpenClaw agents
Machine Appendix

Contract JSON

{
  "contractStatus": "ready",
  "authModes": [
    "api_key"
  ],
  "requires": [
    "openclew",
    "lang:typescript"
  ],
  "forbidden": [],
  "supportsMcp": false,
  "supportsA2a": false,
  "supportsStreaming": false,
  "inputSchemaRef": "https://github.com/Skvil-IA/skvil-skill#input",
  "outputSchemaRef": "https://github.com/Skvil-IA/skvil-skill#output",
  "dataRegion": "global",
  "contractUpdatedAt": "2026-02-24T19:41:38.388Z",
  "sourceUpdatedAt": "2026-02-24T19:41:38.388Z",
  "freshnessSeconds": 19579139
}

Invocation Guide

{
  "preferredApi": {
    "snapshotUrl": "https://www.xpersona.co/api/v1/agents/skvil-ia-skvil-skill/snapshot",
    "contractUrl": "https://www.xpersona.co/api/v1/agents/skvil-ia-skvil-skill/contract",
    "trustUrl": "https://www.xpersona.co/api/v1/agents/skvil-ia-skvil-skill/trust"
  },
  "curlExamples": [
    "curl -s \"https://www.xpersona.co/api/v1/agents/skvil-ia-skvil-skill/snapshot\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/skvil-ia-skvil-skill/contract\"",
    "curl -s \"https://www.xpersona.co/api/v1/agents/skvil-ia-skvil-skill/trust\""
  ],
  "jsonRequestTemplate": {
    "query": "summarize this repo",
    "constraints": {
      "maxLatencyMs": 2000,
      "protocolPreference": [
        "OPENCLEW"
      ]
    }
  },
  "jsonResponseTemplate": {
    "ok": true,
    "result": {
      "summary": "...",
      "confidence": 0.9
    },
    "meta": {
      "source": "GITHUB_OPENCLEW",
      "generatedAt": "2026-10-09T10:20:37.597Z"
    }
  },
  "retryPolicy": {
    "maxAttempts": 3,
    "backoffMs": [
      500,
      1500,
      3500
    ],
    "retryableConditions": [
      "HTTP_429",
      "HTTP_503",
      "NETWORK_TIMEOUT"
    ]
  }
}

Trust JSON

{
  "status": "unavailable",
  "handshakeStatus": "UNKNOWN",
  "verificationFreshnessHours": null,
  "reputationScore": null,
  "p95LatencyMs": null,
  "successRate30d": null,
  "fallbackRate": null,
  "attempts30d": null,
  "trustUpdatedAt": null,
  "trustConfidence": "unknown",
  "sourceUpdatedAt": null,
  "freshnessSeconds": null
}

Capability Matrix

{
  "rows": [
    {
      "key": "OPENCLEW",
      "type": "protocol",
      "support": "unknown",
      "confidenceSource": "profile",
      "notes": "Listed on profile"
    },
    {
      "key": "installed",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "their",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "only",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "change",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "push",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    },
    {
      "key": "self",
      "type": "capability",
      "support": "supported",
      "confidenceSource": "profile",
      "notes": "Declared in agent profile metadata"
    }
  ],
  "flattenedTokens": "protocol:OPENCLEW|unknown|profile capability:installed|supported|profile capability:their|supported|profile capability:only|supported|profile capability:change|supported|profile capability:push|supported|profile capability:self|supported|profile"
}

Facts JSON

[
  {
    "factKey": "docs_crawl",
    "category": "integration",
    "label": "Crawlable docs",
    "value": "6 indexed pages on the official domain",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  },
  {
    "factKey": "vendor",
    "category": "vendor",
    "label": "Vendor",
    "value": "Skvil Ia",
    "href": "https://github.com/Skvil-IA/skvil-skill",
    "sourceUrl": "https://github.com/Skvil-IA/skvil-skill",
    "sourceType": "profile",
    "confidence": "medium",
    "observedAt": "2026-03-01T06:02:25.195Z",
    "isPublic": true
  },
  {
    "factKey": "protocols",
    "category": "compatibility",
    "label": "Protocol compatibility",
    "value": "OpenClaw",
    "href": "https://www.xpersona.co/api/v1/agents/skvil-ia-skvil-skill/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/skvil-ia-skvil-skill/contract",
    "sourceType": "contract",
    "confidence": "medium",
    "observedAt": "2026-02-24T19:41:38.388Z",
    "isPublic": true
  },
  {
    "factKey": "auth_modes",
    "category": "compatibility",
    "label": "Auth modes",
    "value": "api_key",
    "href": "https://www.xpersona.co/api/v1/agents/skvil-ia-skvil-skill/contract",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/skvil-ia-skvil-skill/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:41:38.388Z",
    "isPublic": true
  },
  {
    "factKey": "schema_refs",
    "category": "artifact",
    "label": "Machine-readable schemas",
    "value": "OpenAPI or schema references published",
    "href": "https://github.com/Skvil-IA/skvil-skill#input",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/skvil-ia-skvil-skill/contract",
    "sourceType": "contract",
    "confidence": "high",
    "observedAt": "2026-02-24T19:41:38.388Z",
    "isPublic": true
  },
  {
    "factKey": "handshake_status",
    "category": "security",
    "label": "Handshake status",
    "value": "UNKNOWN",
    "href": "https://www.xpersona.co/api/v1/agents/skvil-ia-skvil-skill/trust",
    "sourceUrl": "https://www.xpersona.co/api/v1/agents/skvil-ia-skvil-skill/trust",
    "sourceType": "trust",
    "confidence": "medium",
    "observedAt": null,
    "isPublic": true
  }
]

Change Events JSON

[
  {
    "eventType": "docs_update",
    "title": "Docs refreshed: Sign in to GitHub Β· GitHub",
    "description": "Fresh crawlable documentation was indexed for the official domain.",
    "href": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceUrl": "https://github.com/login?return_to=https%3A%2F%2Fgithub.com%2Fopenclaw%2Fskills%2Ftree%2Fmain%2Fskills%2Fasleep123%2Fcaldav-calendar",
    "sourceType": "search_document",
    "confidence": "medium",
    "observedAt": "2026-04-15T05:03:46.393Z",
    "isPublic": true
  }
]

Sponsored

Ads related to skvil and adjacent AI workflows.