autonomous-workflow

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

• Third-party content exposure detected (high risk: 0.70). The skill's planner is explicitly allowed to use WebFetch/WebSearch (see CLAUDE.md "Keep the planner high-level" table) and SKILL.md/README describe Phase 1 research/Explore sub-agents and list external "Research Sources" URLs, so the agent can fetch and act on untrusted public web content that can influence plans and downstream actions.