context-ingestion

Warn

Audited by Snyk on Mar 1, 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 explicitly clones and reads a GitHub repository (Step 3: "Clone GitHub Repository") and ingests files from the cloned code and the ethics/ folder (Steps 4–5), meaning it fetches and interprets untrusted public third-party content that can influence downstream analysis and actions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 1, 2026, 07:43 PM