canary-watch
Pass
Audited by Gen Agent Trust Hub on Oct 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: No security concerns were identified within the skill instructions. The behavior described (monitoring URLs for performance and status) is consistent with its stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill processes content from external URLs, which provides a potential surface for indirect prompt injection via website HTML, console logs, or API responses.
- Ingestion points: Deployed URLs provided by the user during monitoring.
- Boundary markers: No specific boundary markers or 'ignore' instructions are defined to encapsulate untrusted web content.
- Capability inventory: This skill contains no executable scripts or tool definitions of its own.
- Sanitization: No explicit sanitization or validation of external web data is described.
Audit Metadata