ratel-integrate

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

• Third-party content exposure detected (low risk: 0.10). SKILL.md’s Step 3/4 instructs the workflow to web-fetch Ratel documentation from docs.ratel.sh and GitHub raw URLs at runtime, which is outsider-authored free text from public web sources ingested by the LLM.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly instructs the agent at runtime to fetch live documentation (e.g., https://docs.ratel.sh/llms.txt and raw GitHub READMEs like https://raw.githubusercontent.com/ratel-ai/ratel/main/README.md) and to trust those fetched docs for deciding integration behavior, so these external URLs are used at runtime and directly control the agent's instructions.