deepseek
Pass
Audited by Gen Agent Trust Hub on Apr 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION]: Uses system commands
curlandjqto perform network requests and process JSON responses from the DeepSeek API. These are standard tools for API interaction. - [EXTERNAL_DOWNLOADS]: Mentions the
openailibrary for Python and Node.js as compatible SDKs for the service. These are well-known and trusted packages from the official registries. - [PROMPT_INJECTION]: The skill acts as a proxy for a remote LLM and handles user input via interpolation into JSON payloads.
- Ingestion points: Untrusted user input is placed into the
messagescontent field withinSKILL.mdexamples. - Boundary markers: None present; uses standard JSON delimiters.
- Capability inventory: The skill uses
curlfor external network communication and writes temporary files to/tmp. - Sanitization: No explicit sanitization or escaping of user input is performed before the API call.
Audit Metadata