qe-github-workflow-automation

Warn

Audited by Snyk on Feb 27, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The SKILL.md templates clearly show the agent fetching and ingesting user-generated GitHub content (e.g., the "PR Validation Swarm" example where gh pr view --json files,labels is passed into npx ruv-swarm actions pr-validate and the RESULTS are then used to post gh pr comment), so untrusted third-party content from public repos can be read and directly influence automated actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 06:10 PM