doc-intel-contract-pl

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

• Third-party content exposure detected (medium risk: 0.30). Skill reads outsider-authored free text from the runtime input for normalization/grounding (e.g., normalize.py ingests --engine inputs via --engine ... input/stdin and passes their extracted text into adapters, then grounding_bridge.py ingests attacker-provided quotes via --quotes).