show-me
Pass
Audited by Gen Agent Trust Hub on Sep 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the system's
opencommand within aBashblock to display generated HTML visualizations to the user. This is a standard functional component for delivering visual artifacts. - [INDIRECT_PROMPT_INJECTION]: The skill acts as a surface for indirect prompt injection by ingesting and rendering content based on the current conversation topic.
- Ingestion points: The skill transforms conversation data into visual formats like Mermaid diagrams and HTML (SKILL.md).
- Boundary markers: The instructions lack specific guidance on using delimiters or markers to separate data from instructions during the visualization process.
- Capability inventory: The skill is capable of executing shell commands to open files (SKILL.md).
- Sanitization: No specific requirements for sanitizing or escaping conversation content are provided before it is included in the generated visuals.
Audit Metadata