pr-review

Pass

Audited by Gen Agent Trust Hub on Nov 16, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONDYNAMIC_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted content from pull request bodies, diffs, and repository feature files to make merging decisions.
  • Ingestion points: The skill reads repo-level configuration files and PR metadata.
  • Capability inventory: The agent can execute shell commands, use the GitHub CLI, and write PR comments.
  • Boundary markers: No explicit delimiters or instructions are used to separate user data from agent instructions.
  • Sanitization: The skill does not validate or sanitize external content before using it to inform logic or execution.
  • [COMMAND_EXECUTION]: The skill utilizes the GitHub CLI (gh) to query repository status, pull request checks, and branch protection rules.
  • [DYNAMIC_EXECUTION]: The skill dynamically executes shell commands extracted from the target repository's docs/agents/review-standards.md file. These commands are used for linting, type checking, and unit testing, providing a mechanism for repository-controlled code execution that could be exploited if the configuration file is modified.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 16, 2026, 02:28 AM