systems-lab-ui
Pass
Audited by Gen Agent Trust Hub on Sep 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill includes a local bash script,
scripts/scaffold-system-canvas.sh, which is used to copy React components and CSS files into a user-specified target directory. The script performs standard local file operations usingmkdirandcpwith basic overwrite protection. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external project documentation and source code to generate visualizations, creating a potential surface for indirect instructions to influence agent behavior.
- Ingestion points: Inspects project code, contracts, documentation, and runtime data as defined in Step 1 of the main workflow in
SKILL.md. - Boundary markers: The instructions do not define specific delimiters or "ignore embedded instructions" warnings for the ingested data.
- Capability inventory: The skill has the capability to execute local shell scripts, modify project files, and use browser-control tools to capture and inspect screenshots.
- Sanitization: There are no explicit instructions or mechanisms described for sanitizing or validating the content extracted from external sources before it is processed.
Audit Metadata