requesting-code-review
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands including git rev-parse, git log, and git diff to identify code changes for review. These are standard operations for a code review tool and are executed within the local environment.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests code changes and implementation descriptions which are then processed by a code-reviewer subagent. This creates a surface for potential indirect prompt injection attacks where malicious code comments or content could attempt to influence the reviewer's analysis.
- Ingestion points: Code changes retrieved via git diff and implementation summaries provided in the description field of the code-reviewer template (SKILL.md, code-reviewer.md).
- Boundary markers: The prompt uses markdown headers to separate sections but lacks explicit boundary delimiters or instructions to ignore embedded commands within the code being analyzed.
- Capability inventory: The skill has the ability to execute git commands and dispatch subagents.
- Sanitization: No sanitization or input validation is performed on the code content before it is passed to the subagent context.
Audit Metadata