api-design

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

• Third-party content exposure detected (low risk: 0.10). The required workflow directs the agent to fetch and read an external SKILL.md file from GitHub.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill instructs fetching runtime instructions from an unofficial GitHub repository, presenting a weak/unknown operational dependency.