paperless-ngx
Pass
Audited by Gen Agent Trust Hub on Feb 18, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill utilizes curl for standard REST API requests (GET, POST, PATCH, DELETE). All commands are documented for specific API endpoints and do not involve suspicious execution patterns such as piping to shell or executing remote scripts.
- [DATA_EXFILTRATION] (SAFE): Document uploads and downloads are limited to the user-provided Paperless-ngx instance. The skill does not access sensitive system files (e.g., SSH keys, AWS credentials) and uses environment variables for the API token, preventing credential exposure.
- [PROMPT_INJECTION] (SAFE): The skill possesses a surface for indirect prompt injection as it ingests data from an external document repository. 1. Ingestion points: API responses from $PAPERLESS_URL/api/documents/. 2. Boundary markers: None present in the documentation. 3. Capability inventory: curl with read/write access to local files and external network access. 4. Sanitization: None specified. This risk is intrinsic to the skill's purpose of document management and is handled as a standard operational characteristic.
Audit Metadata