sig-audit
Pass
Audited by Gen Agent Trust Hub on Aug 8, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill is designed to run local audit and measurement scripts found within the repository. While these are part of the repository's own tooling, the agent will execute them as part of the audit process.
- [PROMPT_INJECTION]: The skill reads and processes potentially untrusted data from the repository (existing audit reports and measurement results). It lacks explicit boundary markers or instructions to ignore embedded commands, which creates a surface for indirect prompt injection if the repository files are tampered with.
- Ingestion points: Measurement results, existing audit reports, and measurement scripts (SKILL.md).
- Boundary markers: None provided.
- Capability inventory: File read/write, local script execution (SKILL.md).
- Sanitization: None observed.
Audit Metadata