canary-watch

Pass

Audited by Gen Agent Trust Hub on Jun 24, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [SAFE]: The skill is composed entirely of documentation (SKILL.md) and contains no executable scripts, binaries, or program logic. No malicious behavior can be executed by the skill in its current form.
  • [DATA_EXPOSURE]: The documentation mentions writing logs to ~/.claude/canary-watch.log. This involves file system operations in a potentially sensitive directory, although it is described as a standard logging mechanism.
  • [DATA_EXPOSURE]: The skill mentions support for Slack and Discord webhooks. If implemented, these would represent network exit points for data collected from the monitored URLs.
  • [PROMPT_INJECTION]: The skill's described purpose (monitoring external URLs, console logs, and API responses) creates an indirect prompt injection attack surface.
  • Ingestion points: Monitored URLs (SKILL.md).
  • Boundary markers: Absent in documentation.
  • Capability inventory: Network requests and file writes (SKILL.md).
  • Sanitization: Absent in documentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 24, 2026, 12:58 PM
Security Audit — agent-trust-hub — canary-watch