antimatter-code-quality-review
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes standard version control tools to facilitate code analysis.
- The agent is instructed to execute
git diffandgit logcommands to identify the specific code changes and commit context for the review. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data as part of its primary function, which represents a potential injection surface.
- Ingestion points: Pull request descriptions, commit messages, issue references, and the source code itself during definition-first reading in Phase 1.
- Boundary markers: The instructions do not specify the use of delimiters or specific safety instructions to isolate external data from the agent's core logic.
- Capability inventory: The skill utilizes file reading, repository-wide search, and git CLI execution to perform its analysis.
- Sanitization: No explicit content sanitization or validation logic is defined to prevent malicious instructions embedded in reviewed code from influencing the agent's behavior.
Audit Metadata