labarchive-integration

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The skill includes examples and workflows that place API keys/passwords directly into config files and command-line arguments (e.g., config.yaml placeholders and a backup command using --password AUTH_TOKEN), which requires the LLM or agent to accept and embed secret values verbatim in generated commands or code, creating an exfiltration risk.

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches and ingests user-generated content from public third-party sites — e.g., references/integrations.md shows import_protocol_to_labarchives calling fetch_protocol_from_protocolsio and inserting protocol_data['html_content'] into LabArchives entries — so the agent would read/interpret untrusted external content.