pr-antipattern-review
Pass
Audited by Gen Agent Trust Hub on May 18, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands including
git,gh,glab,grep, andfindto perform repository analysis and metadata extraction. These operations are restricted to project files and are necessary for the skill's stated purpose of reviewing code diffs. - [EXTERNAL_DOWNLOADS]: The workflow implements a fallback mechanism to fetch pull request diffs via
curl -Lfrom official GitHub and GitLab domains. These requests target well-known services and are used to retrieve the data required for analysis. - [PROMPT_INJECTION]: The skill ingest potentially untrusted data from external sources, specifically code diffs and project blueprint files. This creates an indirect prompt injection surface; however, the skill is designed to perform objective pattern matching and includes mandatory human-in-the-loop checkpoints for any ambiguous interpretations or architectural decisions.
Audit Metadata