malware-detection-and-removal

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md "Repository Investigation" and "Step 2: Content Verification" explicitly require inspecting public GitHub repository metadata and file contents (repo.Description, repo.Topics, repoPath) — untrusted, user-generated third‑party content that the agent must read and that materially drives threat scoring and reporting actions.