epistemic-resourcefulness

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly instructs the agent to retrieve and read authoritative documentation from external/public sources (e.g., OpenAPI/Swagger at /docs or /openapi.json, project repos/README/AGENTS.md, and package registries like PyPI/npm), and then use that content to determine next actions, which exposes it to untrusted third-party content that could carry indirect prompt injections.