Skills
Navigate
skills/koruworks/skills/start-pr-review/Gen Agent Trust Hub

start-pr-review

Pass

Audited by Gen Agent Trust Hub on Oct 28, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes git and gh (GitHub CLI) to inspect code changes, commit history, and to post feedback directly to pull requests.
  • [INDIRECT_PROMPT_INJECTION]: The skill analyzes untrusted data from external sources including code diffs, commit messages, and project documentation which could contain adversarial instructions. 1. Ingestion points: Pull request descriptions, commit messages, and files like PLAN.final.md or PRINCIPLES.md referenced in SKILL.md. 2. Boundary markers: The instructions do not define specific delimiters to separate external content from system instructions. 3. Capability inventory: The skill can execute shell commands (git, gh) and invoke other skills (fix-bug, commit-changes) to modify the repository. 4. Sanitization: No explicit sanitization or filtering of the processed content is specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 28, 2026, 05:28 AM