requesting-code-review

Pass

Audited by Gen Agent Trust Hub on Sep 6, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill instructs a subagent to process external data, creating a surface for indirect prompt injection.
  • Ingestion points: The [DESCRIPTION] and [PLAN_OR_REQUIREMENTS] placeholders in code-reviewer.md, along with the source code retrieved via git diff and git show.
  • Boundary markers: The prompt template uses Markdown section headers to separate instructions from user-provided content.
  • Capability inventory: The reviewer subagent has the ability to execute git commands and perform file system operations such as git worktree add.
  • Sanitization: No specific sanitization or filtering logic is present to prevent embedded instructions within the code or plans from influencing the subagent's behavior.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 6, 2026, 10:41 AM
Security Audit — agent-trust-hub — requesting-code-review