github-bot

Warn

Audited by Snyk on Mar 3, 2026

Risk Level: MEDIUM
Full Analysis

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

  • Third-party content exposure detected (high risk: 0.80). The SKILL.md explicitly instructs the agent to interact with the public GitHub API to list repos, check CI, and manage issues/PRs/comments (user-generated content on GitHub), so the agent will fetch and interpret untrusted third‑party content from GitHub that could materially influence actions like creating or merging PRs.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 3, 2026, 07:59 AM