marshal

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

• Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md) maps "research [topic]" to "search codebase + web → synthesize → report" and describes spawning research sub-agents that gather context, which clearly instructs the agent to fetch and interpret open web content as part of its workflow (exposing it to untrusted third-party content).