warp-ui-skills
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill defines a dependency on external data that the agent is expected to process and follow.
- Ingestion points: The agent is instructed to fetch supplementary visual tokens and guidelines from a remote
DESIGN.mdfile located athttps://github.com/VoltAgent/awesome-design-md/tree/main/design-md/warp. - Boundary markers: The skill does not provide delimiters or instructions to ignore potential malicious content embedded in the remote file.
- Capability inventory: The agent uses these guidelines to generate UI code and layout structures. There is no direct command execution, but the generated code is influenced by external content.
- Sanitization: No sanitization or validation of the fetched markdown content is specified.
- [EXTERNAL_DOWNLOADS]: The skill references and encourages the fetching of content from an external repository not associated with a pre-verified trusted vendor.
- Evidence: "This skill pairs with the corresponding DESIGN.md from awesome-design-md where available: https://github.com/VoltAgent/awesome-design-md/tree/main/design-md/warp"
Audit Metadata