claude-code-headless

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

• Third-party content exposure detected (high risk: 0.90). The skill clearly ingests untrusted third-party content — for example, GitHub PR diffs fetched via gh pr diff in the Integration Patterns (GitHub Actions / shell scripts), optional WebFetch/WebSearch tools referenced in the CLI examples, and the Express.js/FastAPI endpoints that accept arbitrary prompts/tools — and the agent is expected to read and analyze that content as part of its workflow, which can enable indirect prompt injection.