loop-library

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

• Third-party content exposure detected (high risk: 0.75). The skill’s runtime workflow can fetch and ingest the live public catalog from https://signals.forwardfuture.ai/loop-library/catalog.md / catalog.json (outsider-authored public web content) and then uses that text to construct the LLM prompt for loop recommendations.

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

• Potentially malicious external URL detected (high risk: 0.90). The skill explicitly fetches the live catalog at runtime from https://signals.forwardfuture.ai/loop-library/catalog.md and/or https://signals.forwardfuture.ai/loop-library/catalog.json and uses that fetched content as the authoritative source of prompts/instructions for recommending and instantiating published loops, so the external URL directly controls agent prompts and is a required runtime dependency.