joyco-logs

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

• Third-party content exposure detected (low risk: 0.10). The required workflow fetches knowledge indexes and articles via HTTP from hub.joyco.studio, which constitutes reading external web pages rather than automated ingestion of outsider-submitted free text.

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

• Potentially malicious external URL detected (high risk: 0.80). The skill instructs the agent to fetch remote markdown files from hub.joyco.studio at runtime via curl and use their contents to guide its planning and implementation.