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 from an external site (https://basic-anteater-667.convex.site/capabilities.json) and individual capability markdown files, which are provider/publisher-controlled web pages rather than unselected outsider-submitted feeds.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches runtime capability instructions and remote documentation from an arbitrary third-party server (convex.site), representing a weak/unknown operational dependency.