cost-analysis

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.90). The skill requires reading the actual codebase and "show your work" by referencing files and lines (and implicitly quoting code/config) which can force the LLM to surface embedded secrets (API keys, tokens, service-account JSON, .env values) verbatim, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.70). The skill's required workflow explicitly tells the agent to "Use current provider pricing (search the web if needed to confirm rates)" and to "Use current provider pricing" when applying detected providers' pricing, which forces fetching and interpreting open/public third-party web pages (pricing docs) that could contain untrusted content influencing calculations and subsequent actions.