error-message-explainer

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

• Third-party content exposure detected (high risk: 0.80). This skill directly ingests arbitrary, untrusted user-supplied error logs via scripts/parse_errors.py (--file, --stdin, --message) and the interactive paste mode, and parses/interprets that content as part of its workflow, so third-party/user-generated input could carry indirect prompt-injection instructions.