zernio

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes explicit API-key examples (e.g., sk_...) shown being passed verbatim in CLI commands and env exports, which would require an LLM or agent to handle or output secret values directly.

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

• Third-party content exposure detected (medium risk: 0.30). The skill’s runtime CLI workflow exposes inbox/comment/review reading commands (e.g., inbox:messages, inbox:comments, inbox:post-comments, inbox:reviews) that fetch outsider-authored social text (DMs, comments, reviews) from the connected platforms and returns it as JSON for AI agent consumption.