skillzrun

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

• Third-party content exposure detected (high risk: 0.70). Yes — SKILL.md explicitly instructs the agent to fetch and run actions against the external SkillzRun API (e.g., "membrane action run ..." and "membrane request CONNECTION_ID /path/to/endpoint"), which would return third‑party (potentially user‑generated/untrusted) content that the agent is expected to read and could materially influence subsequent actions.