code-review

Pass

Audited by Gen Agent Trust Hub on Sep 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input in the form of code diffs and repository documentation (specs and standards) through specialized sub-agents.
  • Ingestion points: Diff content and repository files are ingested in steps 1, 2, and 3 of the process defined in SKILL.md.
  • Boundary markers: The instructions in step 4 for spawning sub-agents lack explicit delimiters or instructions to ignore potential commands embedded within the diff or spec content.
  • Capability inventory: The skill uses shell commands and has the ability to read arbitrary files within the repository context.
  • Sanitization: No explicit sanitization or filtering logic is defined for the content extracted from the repository before it is processed by the sub-agents.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 22, 2026, 11:39 PM
Security Audit — agent-trust-hub — code-review