headless-cli-agents

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

• Third-party content exposure detected (high risk: 0.90). The skill's agent loop explicitly includes "Gather Context
• Read files, search, web fetch" and the CI/CD example uses allowedTools "Read,Grep,WebSearch", which means the agent will fetch and read open/public web content (untrusted third-party) as part of its workflow.