ah-creator

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). This prompt includes examples that place bearer tokens directly into CLI arguments/JSON (e.g., --config-json '{"port":4123,"bearerToken":"replace-me"}'), which encourages embedding secret values verbatim in generated commands or code and thus risks exfiltration.

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

• Third-party content exposure detected (high risk: 0.90). This skill explicitly documents exposing and interacting with public/remote agents and a public skill registry—see SKILL.md and references/skill-publishing.md commands like "ah agent expose ... --provider agents-hot", "ah discover", "ah call ", and "ah skills install <author/slug>"—which fetch and run or interpret untrusted third-party/user-published content capable of influencing agent behavior.