find-new-curators

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 public third-party content (e.g., morpho-curators.md shows using the public GraphQL endpoint https://blue-api.morpho.org/graphql and an SSR-HTML fallback for https://data.morpho.org/curation, and SKILL.md instructs fetching Lagoon offchain metadata and verifying candidates via public websites, forums, and social media) and then uses that external evidence to drive decisions about adding curator YAMLs and changing classification, so untrusted/user-generated content can materially influence agent actions.