ghwf1-kickoff

Pass

Audited by Gen Agent Trust Hub on Feb 28, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted external data from GitHub issues and pull requests, creating a surface for Indirect Prompt Injection.
  • Ingestion points: Fetches issue body, titles, and comments in Phase 1 and Phase 4 using 'gh issue view' and 'gh pr view' from GitHub.
  • Boundary markers: There are no explicit delimiters or instructions provided to the agent to disregard embedded instructions within the fetched issue content.
  • Capability inventory: The skill has permissions to write to the file system, execute Git commits/pushes, and modify GitHub issue labels and Pull Requests.
  • Sanitization: No sanitization or filtering of external content is mentioned before the agent uses it for brainstorming or document generation.
  • [COMMAND_EXECUTION]: The skill automates several system commands to manage the development environment.
  • Executes 'git' commands for branch creation, commits, and pushing to remote repositories.
  • Uses the 'gh' CLI to interact with GitHub for viewing and editing issues and pull requests.
  • Sources a local initialization script located at '~/.claude/scripts/wf-init.sh'.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 28, 2026, 11:35 PM