skill-content-pipeline

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly asks users for 1–5 reference URLs (Stage 1: "Prompt User for URLs") and then uses the WebFetch tool to retrieve and analyze public web/social content (Stage 2: "Fetch content via WebFetch"), meaning untrusted, user-generated third‑party content is ingested and directly drives analyses and content-generation, enabling indirect prompt injection risk.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 1.00). The skill uses WebFetch to retrieve user-provided external URLs at runtime (i.e., "user-supplied URLs" fetched via WebFetch) and injects that fetched content into the model context for analysis, so external content can directly influence prompts/instructions.