team-lead

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

• Third-party content exposure detected (medium risk: 0.30). The workflow reads tasks from an issue tracker or issue list, which can contain outsider-authored free text ingested automatically without selection.

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

• Potentially malicious external URL detected (high risk: 0.70). The skill references an external repository URL (https://github.com/alonw0/pi-claude-link) for runtime installation via an explicit shell command (pi install), which constitutes an unverifiable external operational dependency with unknown or third-party provenance, resulting in a high tier.