content-pillar-atomizer

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

• Third-party content exposure detected (high risk: 0.80). The skill's workflow explicitly says "If URL provided, use web_fetch to retrieve content" for the pillar_content field, meaning it will fetch and ingest arbitrary public web pages/URLs and then read and act on that untrusted third‑party content to generate platform-native posts (Step 1 in SKILL.md), creating a clear avenue for indirect prompt injection.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill explicitly calls web_fetch on a user-supplied pillar_content URL at runtime (e.g., any http(s) URL or git reference such as https://... or git@github.com:org/repo.git), and the fetched content is injected into the model context to drive generation, so external URLs can directly control agent prompts.