requesting-code-review

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses local shell commands to interact with the git version control system.\n
  • Evidence: Uses git rev-parse and git log in SKILL.md to identify commit SHAs, and git diff in code-reviewer.md to retrieve the code changes for analysis.\n- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it processes un-sanitized external content such as code diffs and task descriptions.\n
  • Ingestion points: User-provided descriptions and code content from the repository are interpolated into the subagent's system prompt in code-reviewer.md via placeholders like {DESCRIPTION} and the output of git diff.\n
  • Boundary markers: Missing. The template uses simple placeholders without delimiters or instructions to ignore embedded commands.\n
  • Capability inventory: The skill is capable of executing git commands (git diff, git log, git rev-parse).\n
  • Sanitization: No sanitization or escaping is performed on the input variables before they are passed to the subagent.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 08:35 AM