plan-reviewer
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted work plans provided by users, which constitutes a potential attack surface. Ingestion points: Plans are passed inline as described in SKILL.md. Boundary markers: None present. Capability inventory: The agent is instructed to open referenced files to verify their contents. Sanitization: None present.
- [SAFE]: The skill contains no executable code, obfuscation, or evidence of malicious intent.
Audit Metadata