cli-plugins-skills

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt repeatedly documents a --api-key CLI flag (and similar token flags), which encourages passing secrets as command-line arguments and would require the LLM to place secret values verbatim into generated commands—an insecure pattern that risks exfiltration.

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow for this skill is a CLI that manages/install/search “skills” and “plugins” (e.g., skills install <packageId> / skills install <url> / plugin install <name>), which can fetch and ingest outsider-authored free text from public/community marketplaces or arbitrary URLs into the agent’s LLM context when executing installed skills.