review-coverage
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION] (LOW): The skill executes
git diffcommands to identify changed files and content. This is a standard subprocess execution for development tools and is restricted to local Git operations. - [PROMPT_INJECTION] (LOW): The skill has an indirect prompt injection surface because it ingests and processes untrusted source code. Malicious instructions embedded in code comments could potentially influence the agent's behavior or reporting.
- Ingestion points: Local source files and Git diff output (SKILL.md Step 2 & 3).
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the files it reviews.
- Capability inventory: Limited to file reading and local read-only Git commands.
- Sanitization: No sanitization or filtering of the ingested source code is performed.
Audit Metadata