prism-chart
Pass
Audited by Gen Agent Trust Hub on Jul 1, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The workflow executes the
prism_agent.uiuxPython module via theBashtool to search the chart knowledge base. - [PROMPT_INJECTION]: The skill interpolates user-provided input into a shell command query string, creating a surface for potential indirect prompt injection.
- Ingestion points: User-provided data type enters the agent context through the
{data_type}variable in SKILL.md. - Boundary markers: No delimiters or ignore instructions are used to wrap the user input.
- Capability inventory: The skill has access to the
Bashtool for command execution. - Sanitization: No sanitization or escaping of the
{data_type}variable is mentioned before execution.
Audit Metadata