llm-wiki

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill prompt instructs the agent to log in using --password '<password>' on the command line, which handles user credentials insecurely.

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

• Third-party content exposure detected (low risk: 0.10). The workflow ingests arbitrary URLs and documents via web_extract during the ingest process, falling under low indirect prompt injection risk.

MEDIUM W013: Attempt to modify system services in skill instructions.

• Attempt to modify system services in skill instructions detected (high risk: 0.70). The skill prompt suggests modifying systemd user services and running a sudo command (sudo loginctl enable-linger $USER) to configure background sync.