review
Pass
Audited by Gen Agent Trust Hub on Mar 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Executes shell commands including
git branch,git fetch, andgit diffto retrieve repository metadata and code changes for the review process. - [PROMPT_INJECTION]: The skill processes untrusted input from git diffs, which presents a surface for indirect prompt injection where an attacker could embed instructions in comments or code to influence the agent's review logic.
- Ingestion points: Reads untrusted code changes via
git diff origin/mainas specified inSKILL.md. - Boundary markers: Absent; the workflow does not employ delimiters or specific instructions to ignore embedded commands within the diff content.
- Capability inventory: Executes
gitcommands and can modify local files if the user selects a "Fix it now" option (SKILL.md). - Sanitization: None; the agent operates directly on the raw diff output without filtering or validation.
Audit Metadata