base

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill explicitly instructs the agent to ask for, read and parse a user's centralized access file and "create project .env with found keys," which requires handling and emitting secret values verbatim (high exfiltration risk).

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 0.90). The content is largely benign coding and TDD guidance but contains a high-risk credential-handling directive that tells the assistant to ask for, read, parse, validate, and import users' centralized access files (API keys), which creates a strong risk of data exfiltration and credential theft if misused.