review-code
Pass
Audited by Gen Agent Trust Hub on May 9, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands using
gitandgh(GitHub CLI) to retrieve code diffs and file contents. These operations are aligned with the skill's purpose of code analysis. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) because it ingests untrusted code data into the agent's context.
- Ingestion points: Untrusted code content and diffs are retrieved via
gh pr diff,git show, and standard file read operations. - Boundary markers: Absent. The instructions do not specify the use of delimiters or clear separation between the agent's system instructions and the untrusted code content being analyzed.
- Capability inventory: The skill uses
git,gh,grep, andread. It is primarily focused on analysis and does not demonstrate capabilities for code modification or unauthorized network exfiltration. - Sanitization: Absent. The skill does not mention any sanitization or filtering of the code content before it is processed by the specialist agents.
Audit Metadata