foundations-safety-engineering
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill references a primary source handbook hosted on a Massachusetts Institute of Technology (MIT) server. This is a legitimate academic reference used for methodology verification.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted system descriptions in SKILL.md and assets/templates/safety-traceability.md. It lacks explicit boundary markers or sanitization logic. However, the skill has no capability for subprocess execution, network operations, or file-writing, which significantly limits the risk.
Audit Metadata