light-design
Pass
Audited by Gen Agent Trust Hub on Nov 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill implements research planning workflows with a focus on data integrity. It includes a utility script for verifying the consistency of project artifacts using SHA256 fingerprinting.
- [COMMAND_EXECUTION]: The skill provides shell commands for a local Python utility (design_bridge.py) used to initialize workspaces and verify data. These are standard developer tools and do not pose a risk of unauthorized execution or privilege escalation.
- [INDIRECT_PROMPT_INJECTION]: While the skill ingests external research data, it explicitly instructs the agent to treat such content as data rather than executable instructions. It also uses cryptographic hashes to ensure that inputs match previously reviewed states.
- [EXTERNAL_DOWNLOADS]: The skill references several well-known scientific repositories and publications for methodological guidance. The documentation confirms these resources are for static reference only and are not executed by the agent.
Audit Metadata