judge-arch
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands to perform its primary function. Specifically, it runs
git diff <base>...HEADto identify changes between the current branch and a base branch. This is an expected and legitimate use of shell execution for a code review tool. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from repository files which could contain embedded instructions intended to influence the agent's judgment.
- Ingestion points: Reads content from
DECISIONS.md, the output ofgit diff, and the content of all changed files in the repository. - Boundary markers: None. The skill does not use specific delimiters to separate user data from its own internal instructions.
- Capability inventory: The skill has the ability to read arbitrary files within the repository and execute git commands via the shell.
- Sanitization: No sanitization, escaping, or filtering of the file contents is performed before the agent processes them.
Audit Metadata