hermes-attestation-guardian

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and parses external advisory feeds (see lib/feed.mjs's fetchTextRequired/fetchTextOptional and DEFAULT_REMOTE_FEED_URL plus env/config overrides like HERMES_ADVISORY_FEED_URL) and scripts such as scripts/refresh_advisory_feed.mjs and scripts/guarded_skill_verify.mjs read and act on that cached feed to gate installs and decisions, so untrusted third‑party feed content can materially influence behavior.