quality-gate
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands (git rev-parse, git log, git diff) to identify code changes between two points in history. These commands are necessary for the skill's primary function of code review and are executed within the local repository context.
- [INDIRECT_PROMPT_INJECTION]: The code reviewer subagent processes external data in the form of git diff outputs and implementation descriptions. This creates a surface where malicious instructions embedded in the code being reviewed (e.g., in comments) could potentially influence the reviewer's verdict.
- Ingestion points: git diff output and placeholder values ({WHAT_WAS_IMPLEMENTED}, {PLAN_OR_REQUIREMENTS}) in
code-reviewer.md. - Boundary markers: The instructions use markdown headers to separate context, but lack specific 'ignore embedded instructions' delimiters for the diff content.
- Capability inventory: The skill uses
git diffto read file contents for analysis. - Sanitization: No filtering or sanitization is performed on the code content before it is processed by the agent.
Audit Metadata