openhook

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

• Third-party content exposure detected (medium risk: 0.30). The agent skill monitors and consumes incoming messages from Openhook channels where outsider peers can submit text.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs the agent to run code fetched from an external remote repository via uv run --locked openhook-channel-listen --url https://openhook.dev, constituting an unverifiable operational runtime dependency.