strk20-privacy

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches and executes arbitrary web pages and repositories via HTTP requests in check_freshness.py, but does not ingest outsider-authored free text into any automated agent queue.

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

• Potentially malicious external URL detected (medium risk: 0.30). The script in scripts/check_freshness.py performs runtime requests to external URLs (npm registry, GitHub raw content, wallet specifications, and documentation domains) to fetch data used in checks, which constitutes an operational inbound dependency on external sources.