time-tracking
Pass
Audited by Gen Agent Trust Hub on Feb 20, 2026
Risk Level: SAFE
Full Analysis
- SAFE (SAFE): No malicious patterns or security risks were identified. The skill correctly utilizes 1Password for secret management rather than hardcoding credentials.
- PROMPT_INJECTION (LOW): Evaluation of indirect prompt injection surface:
- Ingestion points: User-controlled strings for task descriptions and project names in the
scripts/trackcommand. - Boundary markers: Instructions use double-quotes in command examples to delimit user-provided text.
- Capability inventory: Execution of the local script
scripts/track, which likely performs authorized API calls to Toggl or Clockify. - Sanitization: The skill relies on standard shell quoting in its documentation to prevent basic injection; the internal script implementation is expected to handle string parsing securely.
Audit Metadata