labarchive-integration

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 0.80). The prompt includes examples that embed credentials directly (config.yaml with access_password and a CLI example using --password AUTH_TOKEN), which encourages putting secrets verbatim into generated commands/code and thus creates an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md explicitly instructs the agent to call LabArchives REST API endpoints (e.g., https://api.labarchives.com/api and specific methods like users/user_access_info and notebooks/notebook_backup) to fetch notebook entries, attachments and other user-generated content which the workflows parse and act on (backups, entry creation, uploads), thereby exposing the agent to untrusted third-party content that could contain indirect instructions.