conda-recipe

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

• Third-party content exposure detected (high risk: 0.70). The skill explicitly instructs checking and using external source URLs and project pages (e.g., PyPI/GitHub URLs in meta.yaml, downloading source tarballs, verifying source URL accessibility and checksums, and reviewing CircleCI/build logs), which are untrusted public third‑party contents the agent would read or interpret as part of its workflow.