requesting-code-review

Pass

Audited by Gen Agent Trust Hub on Sep 4, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes external data which could potentially contain malicious instructions intended to bypass subagent guidelines. 1. Ingestion points: The code-reviewer.md template interpolates user-provided implementation details, plan references, and the output of git diff commands. 2. Boundary markers: Absent. The template does not employ specific delimiters or 'ignore' instructions to isolate the ingested content from the subagent's logic. 3. Capability inventory: The subagent in code-reviewer.md has the ability to execute shell commands (git diff) and provide assessments. 4. Sanitization: Absent. Content from code changes and planning files is treated as trusted technical input.
  • [COMMAND_EXECUTION]: The skill utilizes local shell commands to interact with the repository. Evidence includes the use of git rev-parse, git log, and git diff within SKILL.md and code-reviewer.md. These operations are restricted to the local filesystem and are consistent with the skill's primary purpose.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 4, 2026, 06:55 AM
Security Audit — agent-trust-hub — requesting-code-review