uitripled

Pass

Audited by Gen Agent Trust Hub on Mar 29, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill instructs the agent to use a CLI tool to install components, which involves downloading and executing code from a community repository.
  • Evidence: SKILL.md and integration patterns describe the use of npx uitripled to fetch component files from the moumen-soliman/uitripled repository.
  • Risk: Relying on an unverified community source for executable code poses a potential supply chain risk, as the package is not from a recognized trusted vendor or well-known service.
  • [PROMPT_INJECTION]: The skill provides components for AI Chat and search interfaces, which represent surfaces for indirect prompt injection.
  • Ingestion points: AI Chat Interface and Expanding Search Dock components (catalogued in SKILL.md).
  • Boundary markers: No delimiters or instructions are provided in the documentation to isolate user data from agent prompts when using these components.
  • Capability inventory: The CLI tool associated with the skill has the capability to write to the file system and access the network.
  • Sanitization: The documentation lacks evidence of sanitization or validation routines for data processed and rendered by these interactive UI components.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 29, 2026, 05:50 PM