jmb-code-review
Pass
Audited by Gen Agent Trust Hub on Nov 21, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands to interact with the Git version control system, including
git diff,git log, andgit rev-parse. These are standard operations for a code review tool and are used to gather data for analysis. - [INDIRECT_PROMPT_INJECTION]: The skill ingests and processes untrusted data from the repository being reviewed, which could be exploited to influence the agent's behavior.
- Ingestion points: Untrusted data enters the agent context through the output of
git diff(code changes),git log(commit messages), and local repository files (e.g., specifications and standards documents). - Boundary markers: The instructions for spawning sub-agents do not specify the use of clear delimiters (like XML tags or triple quotes) or explicit instructions for the agent to ignore instructions embedded within the diff content.
- Capability inventory: The skill has the capability to execute read-only Git commands and perform file system reads to retrieve documentation.
- Sanitization: There is no evidence of sanitization or escaping of the diff content or commit messages before they are interpolated into the sub-agent prompts.
Audit Metadata