case-study-writing
Pass
Audited by Gen Agent Trust Hub on Apr 22, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: References installation instructions for the vendor's CLI hosted on the official GitHub repository for 'inference-shell'.
- [COMMAND_EXECUTION]: Employs the 'infsh' CLI for utility tasks including authentication, application management, and executing research-oriented modules.
- [REMOTE_CODE_EXECUTION]: Executes a Python script via the 'infsh/python-executor' tool to generate charts using the 'matplotlib' library. The script is defined locally within the skill and performs benign data visualization tasks.
- [INDIRECT_PROMPT_INJECTION]: The skill processes data from external search providers like Tavily and Exa for industry research. • Ingestion points: Research data returned by 'tavily/search-assistant' and 'exa/search'. • Boundary markers: No explicit delimiters or instructions are provided to the agent to treat external search results as untrusted content. • Capability inventory: File system access (via 'matplotlib' saving charts) and tool execution via 'infsh'. • Sanitization: No explicit validation or filtering of the external search data is implemented within the skill instructions.
Audit Metadata