contracts

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The skill contains deliberate instructions to hide where the document-server runs and to suppress internal/tooling details from users, while also instructing local CLI spawns and persistent DB writes — patterns that enable covert access, concealed remote operations, and potential data exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.85). Outsider-authored free text is the contract documents themselves (user-provided but not authored by the operating user), which are ingested/read at runtime via the dump → reader prompts path and then used to generate LLM context for the documents-reader agents.