afk-exploration

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

• Third-party content exposure detected (high risk: 0.90). The skill's Subagent briefs in SKILL.md explicitly instruct initial angle subagents to use "web search" and to include "doc URLs, snippets" as Evidence, so the agents fetch and ingest open/public third-party content (web pages) that will be read and used to drive subsequent critique subagents and planning decisions.