lang-typescript

Pass

Audited by Gen Agent Trust Hub on Feb 16, 2026

Risk Level: LOW
Full Analysis
  • [Indirect Prompt Injection] (INFO): The skill processes project-specific files which are technically untrusted data, but its capabilities are restricted to standard development workflows.
  • Ingestion points: Reads project files including tsconfig.json, justfile, eslint.config.js, and .ts/.tsx source files to inform the agent's strategy.
  • Boundary markers: Not explicitly defined; the skill relies on the agent's internal logic to separate instructions from code content.
  • Capability inventory: Includes executing build and test commands via bun, tsc, and vitest, and performing targeted cache cleanup (rm -rf .vinxi .output).
  • Sanitization: None explicitly defined in the skill markdown.
  • [COMMAND_EXECUTION] (SAFE): The identified commands (bun run, tsc --noEmit, vitest) are standard industry practices for the stated purpose of the skill and do not involve unauthorized privilege escalation or suspicious network activity.
  • [EXTERNAL_DOWNLOADS] (SAFE): Documentation retrieval uses a trusted pattern (MCP) targeting reputable sources such as Microsoft and SolidJS.
Audit Metadata
Risk Level
LOW
Analyzed
Feb 16, 2026, 09:41 AM