code-review

Pass

Audited by Gen Agent Trust Hub on Aug 30, 2026

Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill content is purely instructional and does not contain any code, command execution, or remote resource requests.
  • [INDIRECT_PROMPT_INJECTION]: The skill instructions involve analyzing external data such as pull requests and issues. This represents a minimal attack surface because the skill has no tools or execution capabilities. Ingestion points: SKILL.md (Instructions to read PR description/issues). Boundary markers: Absent. Capability inventory: None (The skill lacks tool access or shell execution). Sanitization: Absent.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 30, 2026, 10:29 PM
Security Audit — agent-trust-hub — code-review