data-visualization
Pass
Audited by Gen Agent Trust Hub on Apr 14, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
infshCLI tool for administrative tasks such as logging in and executing remote applications. - [EXTERNAL_DOWNLOADS]: The skill references installation scripts and additional modular skills hosted on the
inference-shGitHub repository. - [REMOTE_CODE_EXECUTION]: The skill provides templates for sending Python code and HTML snippets to be executed on remote cloud infrastructure via the
python-executorandhtml-to-imageapps. - [PROMPT_INJECTION]: The skill contains a surface for indirect prompt injection (Category 8) due to the interpolation of data into code execution templates.
- Ingestion points: Data used in visualization charts (e.g., labels, titles, and values).
- Boundary markers: None; the skill does not instruct the agent to use delimiters or ignore instructions within the processed data.
- Capability inventory: The skill allows shell command execution and remote Python code execution.
- Sanitization: None; the examples do not demonstrate validation or escaping of input data before it is embedded in executable code strings.
Audit Metadata