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 ingesting outsider-authored or dynamically served web content via an active fetch.

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

• Potentially malicious external URL detected (medium risk: 0.30). The skill fetches a remote capability catalog from an unofficial third-party domain (convex.site) at runtime to guide agent behavior and dynamically load procedures.