canary-watch

Pass

Audited by Gen Agent Trust Hub on May 16, 2026

Risk Level: SAFENO_CODEPROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns, obfuscation, or unauthorized data access detected.
  • [NO_CODE]: The skill consists exclusively of markdown instructions and does not include any executable scripts or binary files.
  • [PROMPT_INJECTION]: The skill processes untrusted content from external URLs, which is a potential surface for indirect prompt injection.
  • Ingestion points: External URLs provided to the agent for monitoring (SKILL.md).
  • Boundary markers: None; the instructions do not define delimiters for external data.
  • Capability inventory: Browser tools (implicit) and file system writes to a log file (~/.claude/canary-watch.log).
  • Sanitization: No content sanitization or validation rules are specified.
Audit Metadata
Risk Level
SAFE
Analyzed
May 16, 2026, 03:54 AM
Security Audit — agent-trust-hub — canary-watch