agent-orchestrator

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 invoke a web-fetch (e.g., "$web-fetch-md ") when a matching skill is needed and to identify/consume authoritative sources, which requires fetching and interpreting arbitrary public URLs whose content could influence agent decisions (SKILL.md, Workflow steps 1–2).