taku-review
Pass
Audited by Gen Agent Trust Hub on May 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to execute local git commands, such asgit remote get-url,git status, andgit diff, to inspect the repository and identify code changes. - [PROMPT_INJECTION]: The skill possesses an indirect prompt injection attack surface because it ingests untrusted data from code diffs and documentation while maintaining the ability to edit files and execute shell commands.
- Ingestion points: Git diffs and project documentation (e.g.,
PLAN.md,DESIGN.md). - Boundary markers: The skill does not implement specific delimiters or instructions to ignore commands potentially embedded within the code diffs it reviews.
- Capability inventory: Use of
Bash,Edit,Write,Read,Grep, andGlobtools. - Sanitization: No explicit sanitization or filtering is provided for the content retrieved from the diffs or external documentation.
Audit Metadata