mpstats

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The skill prompt instructs the agent to have the user send the token in chat and then create the environment file itself, which exposes the secret value directly in the LLM's context and output.

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

• Third-party content exposure detected (medium risk: 0.30). The workflow retrieves product reviews and comments via MPSTATS API endpoints (items/{id}/comments and brand feedback comments) which contain outsider-authored free text.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The script scripts/wb/wb-card-content.sh executes an operational runtime fetch against a wildcard Wildberries CDN endpoint (basket-N.wbbasket.ru), representing an unverifiable third-party external dependency.