data-visualization

Pass

Audited by Gen Agent Trust Hub on Apr 23, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: Instructs the agent to use the infsh CLI for session management and to run specific applications for data processing.
  • [REMOTE_CODE_EXECUTION]: Dynamically generates and executes Python code and HTML/CSS using the vendor's remote executors (infsh/python-executor and infsh/html-to-image) to produce images and charts.
  • [EXTERNAL_DOWNLOADS]: References installation scripts and additional skill packages hosted on the author's official GitHub repository (inference-sh).
  • [PROMPT_INJECTION]: Identifies an indirect prompt injection surface as the skill processes external data for code generation. Ingestion points: Processes data into Matplotlib code snippets. Boundary markers: None present in the provided templates. Capability inventory: Shell command execution and remote code execution via infsh. Sanitization: Not explicitly implemented in the provided examples, relying on the underlying model's safety constraints.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 23, 2026, 07:52 AM