convex-add

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

• Third-party content exposure detected (low risk: 0.10). The workflow fetches a capability catalog and individual capability documents from a remote site (https://basic-anteater-667.convex.site), which are treated as external third-party sources of text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches behavior-selecting instructions and capability documents from an arbitrary Convex site URL (https://basic-anteater-667.convex.site/capabilities.json), presenting a weak/unknown provenance operational dependency.