reviewer-correctness
Pass
Audited by Gen Agent Trust Hub on Jul 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill performs shell-level operations using
git diffto retrieve code changes for analysis. It also executes project-specific quality gates as defined in the environment'sCLAUDE.mdfile, which is standard for automated code review tasks. - [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface because it processes untrusted content from source code diffs.
- Ingestion points: Code diffs are ingested via
git diffcommands inSKILL.md. - Boundary markers: No specific delimiters are used to wrap the diff content or warn the agent to ignore embedded instructions.
- Capability inventory: The skill can execute quality gate scripts and manage issues via the
bdtool as seen inSKILL.md. - Sanitization: No evidence of sanitization or escaping was found for the data ingested from code diffs.
Audit Metadata