sartre

Pass

Audited by Gen Agent Trust Hub on Jul 17, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: No security issues detected. The skill defines a persona using standard instructions and a reference file. It restricts its own capabilities by limiting allowed tools to 'Read' and 'AskUserQuestion'.
  • [PROMPT_INJECTION]: The skill processes user dialogue which serves as an indirect prompt injection surface. However, the risk is negligible as the skill lacks high-privilege capabilities or network access.
  • Ingestion points: User dialogue and local files accessed via the 'Read' tool in SKILL.md.
  • Boundary markers: None explicitly defined to separate system instructions from processed data.
  • Capability inventory: Limited to reading files and interacting with the user; no shell execution, network operations, or persistence mechanisms are requested (SKILL.md).
  • Sanitization: No explicit sanitization or validation of external input is implemented.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 17, 2026, 12:05 PM
Security Audit — agent-trust-hub — sartre