implementing-issues

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

• Third-party content exposure detected (high risk: 0.90). The skill explicitly fetches and reads user-authored issue/ticket content (e.g., via "gh issue view --json ..." and "linear-cli issue ") and instructs the agent to "Read and understand issue requirements" and act (implement code, create branches/PRs) based on that content, exposing it to untrusted third-party input that could inject instructions.