plan-ci

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly instructs the agent to "Fetch — Download CI logs from GitHub Actions" and to "use the planner subagent to read the github actions logs" (SKILL.md), which requires ingesting untrusted, user-generated GitHub Actions logs and using their content to drive analysis and planning, enabling indirect prompt-injection risk.