convex-check-updates

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

• Third-party content exposure detected (low risk: 0.10). The workflow reads component metadata and summaries from the anteater registry via an external script, which can contain outsider-authored text from public registry listings.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches and executes an arbitrary remote script from a weak unstructured domain via curl, representing a weak/unknown operational dependency.