qe-github-workflow-automation

Pass

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill frequently uses npx to download and execute code from the ruv-swarm and claude-flow packages at runtime. These packages originate from the ruvnet organization, which is not listed as a trusted vendor.
  • [COMMAND_EXECUTION]: The skill generates and executes shell commands using the gh (GitHub CLI) and various npx tools to manage repositories, create issues, and modify workflows.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8).
  • Ingestion points: The skill reads untrusted external data using gh run view, gh pr view, and npx ruv-swarm actions analyze-codebase.
  • Boundary markers: No specific boundary markers or 'ignore embedded instructions' prompts are defined in the provided templates to isolate processed data from the system instructions.
  • Capability inventory: The skill possesses extensive capabilities including creating GitHub issues (gh issue create), commenting on PRs (gh pr comment), and modifying workflow files.
  • Sanitization: There is no evidence of sanitization or validation of the data retrieved from GitHub before it is passed to the AI swarm agents for analysis or action.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 27, 2026, 06:09 PM