skill-web-research

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

• Third-party content exposure detected (high risk: 0.80). The skill's Stage 5 "Invoke Subagent" requires spawning the web-research-agent which is explicitly instructed to "search web for framework documentation" and analyze those findings, meaning the agent will fetch and interpret content from open/public third-party sites as part of its workflow (potentially influencing recommendations and artifacts).