code-review-and-refactor
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
gitcommands such asgit diff,git log, andgit statusto retrieve source code changes and repository history for analysis. - [EXTERNAL_DOWNLOADS]: Instructions include a recommendation for the user to install the
publish-messageskill from the author's GitHub repository (Dyrits/SKILLS) using thenpx skillscommand. - [INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it ingests untrusted data from git diffs, commit messages, and external documentation files. Ingestion points: Git diffs, commit messages, and repository documentation files (e.g.,
CODING_STANDARDS.md,GLOSSARY.md). Boundary markers: Not explicitly defined in the instructions for separating untrusted data from instructions. Capability inventory: Includes file system reads/writes (refactoring) and execution of git commands. Sanitization: No explicit sanitization or filtering of the processed content is mentioned.
Audit Metadata