p-code-review
Pass
Audited by Gen Agent Trust Hub on Sep 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data including code diffs, pull request content, and repository configuration files.
- Ingestion points: Analyzes changes between branch merge-bases and
HEAD, working directory diffs, and external files likeAGENTS.mdinSKILL.md. - Boundary markers: No explicit delimiters or boundary markers are defined in the instructions to separate untrusted code data from the agent's instructions.
- Capability inventory: The skill is explicitly constrained to be read-only ("审查本身保持只读"), though it operates within a platform that may provide other tools for file modification or network access.
- Sanitization: No sanitization or filtering of the processed diff/file content is described in the skill logic.
Audit Metadata