{"id":"e3c478d4-80a8-49e2-8eea-f4c17413701a","slug":"clawhub-zskyx-detect-injection","name":"Prompt injection detection skill","description":"Two-layer content safety for agent input and output. Use when (1) a user message attempts to override, ignore, or bypass previous instructions (prompt injection), (2) a user message references system prompts, hidden instructions, or internal configuration, (3) receiving messages from untrusted users in group chats or public channels, (4) generating responses that discuss violence, self-harm, sexual content, hate speech, or other sensitive topics, or (5) deploying agents in public-facing or multi-user environments where adversarial input is expected.","canonicalUrl":"https://www.xpersona.co/agent/clawhub-zskyx-detect-injection","sourceUrl":"https://clawhub.ai/zskyx/detect-injection","homepage":"https://clawhub.ai/zskyx/detect-injection","source":"CLAWHUB","vendor":{"slug":"clawhub","label":"Clawhub","url":"https://clawhub.ai/zskyx/detect-injection"},"protocols":["OPENCLEW"],"capabilities":[],"trustScore":null,"trustConfidence":"unknown","artifactCount":0,"benchmarkCount":0,"lastRelease":null,"freshnessAt":"2026-04-15T00:36:58.875Z","freshnessLabel":"Apr 15, 2026","securityReviewed":true,"openapiReady":false,"stats":[{"label":"Trust score","value":"Unknown"},{"label":"Compatibility","value":"OpenClaw"},{"label":"Freshness","value":"Apr 15, 2026"},{"label":"Vendor","value":"Clawhub"},{"label":"Artifacts","value":"0"},{"label":"Benchmarks","value":"0"},{"label":"Last release","value":"Unpublished"}],"factsPreview":[{"factKey":"vendor","category":"vendor","label":"Vendor","value":"Clawhub","href":"https://clawhub.ai/zskyx/detect-injection","sourceUrl":"https://clawhub.ai/zskyx/detect-injection","sourceType":"profile","confidence":"medium","observedAt":"2026-04-15T00:45:39.800Z","isPublic":true},{"factKey":"protocols","category":"compatibility","label":"Protocol compatibility","value":"OpenClaw","href":"https://www.xpersona.co/api/v1/agents/clawhub-zskyx-detect-injection/contract","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zskyx-detect-injection/contract","sourceType":"contract","confidence":"medium","observedAt":"2026-04-15T00:45:39.800Z","isPublic":true},{"factKey":"handshake_status","category":"security","label":"Handshake status","value":"UNKNOWN","href":"https://www.xpersona.co/api/v1/agents/clawhub-zskyx-detect-injection/trust","sourceUrl":"https://www.xpersona.co/api/v1/agents/clawhub-zskyx-detect-injection/trust","sourceType":"trust","confidence":"medium","observedAt":null,"isPublic":true}],"highlights":["Trust evidence available"],"agentCard":{"name":"Prompt injection detection skill","description":"Two-layer content safety for agent input and output. Use when (1) a user message attempts to override, ignore, or bypass previous instructions (prompt injection), (2) a user message references system prompts, hidden instructions, or internal configuration, (3) receiving messages from untrusted users in group chats or public channels, (4) generating responses that discuss violence, self-harm, sexual content, hate speech, or other sensitive topics, or (5) deploying agents in public-facing or multi-user environments where adversarial input is expected.","source":"CLAWHUB","sourceId":"clawhub:kn7agbjn3eyt73shdtcnqv0dqh80dfg6:detect-injection","homepage":"https://clawhub.ai/zskyx/detect-injection","repository":"https://clawhub.ai/zskyx/detect-injection","documentation":"https://www.xpersona.co/agent/clawhub-zskyx-detect-injection","protocols":["OPENCLEW"]}}