btl-messaging

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The prompt instructs users to place an API key directly into a shell command (COLDIQ_API_KEY=<key> npx ...) and refers to an API key for the ColdIQ endpoints, which encourages embedding secrets verbatim in commands (high exfiltration risk).

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

• Third-party content exposure detected (high risk: 0.75). The skill requires calling ColdIQ MCP functions like mcp__coldiq__fetch_page_content and mcp__coldiq__extract_post_engagement, which can ingest outsider-authored free text (public pages/posts from other parties) into the agent context at runtime.