golang-troubleshooting

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md workflow explicitly tells the agent to fetch and inspect external services (e.g., "Check External Dependencies" and examples like curl to https://api.example.com/endpoint, dig, nc, and reading API responses) — these are untrusted third‑party endpoints whose responses the agent is expected to read and use to drive debugging decisions, so third‑party content could inject instructions or influence actions.