skills/shotaiuchi/dotclaude/ghwf7-pr/Gen Agent Trust Hub

ghwf7-pr

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface by ingesting untrusted data from external sources.\n
  • Ingestion points: The skill fetches user-controllable data (body and comments) from GitHub via gh issue view and gh pr view in the 'Load Context' step.\n
  • Boundary markers: There are no boundary markers or 'ignore' instructions specified to prevent the agent from being influenced by instructions embedded within the fetched comments.\n
  • Capability inventory: The agent has the capability to execute state-changing commands including gh pr ready, gh pr edit, gh issue edit, and gh pr comment.\n
  • Sanitization: No sanitization, validation, or escaping logic is defined for the content retrieved from GitHub before it is processed or used in subsequent steps.\n- [COMMAND_EXECUTION]: The skill uses the GitHub CLI (gh) to automate Pull Request and Issue management.\n
  • Evidence: Processing steps involve executing gh commands to transition PR status, edit titles, and modify labels to match the workflow state.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 11:34 PM