convex

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 URL (https://basic-anteater-667.convex.site/capabilities.json?src=agent-skills), which involves fetching external content over the network categorized under low risk.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill fetches a remote capability catalog from a third-party site (https://basic-anteater-667.convex.site/) whose content governs agent behavior and provides operational runtime instructions, constituting an unverifiable third-party dependency.