skills/tanstack/ai/tanstack-ai/Gen Agent Trust Hub

tanstack-ai

Pass

Audited by Gen Agent Trust Hub on Sep 9, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill uses npx @tanstack/intent@latest to fetch and execute the TanStack Intent CLI tool for project analysis and skill configuration.
  • [COMMAND_EXECUTION]: Instructions direct the agent to run package management commands (e.g., pnpm add, npm install) and Node.js snippets to inspect package versions and repository files.
  • [INDIRECT_PROMPT_INJECTION]: The skill acts as a router that ingests content from installed packages and external skill files, representing an attack surface for indirect prompt injection if those resources were compromised.
  • Ingestion points: Reads files from node_modules/@tanstack and loads additional skill definitions via npx @tanstack/intent load.
  • Boundary markers: The skill does not define specific delimiters for content loaded from external sources.
  • Capability inventory: Execution of shell commands (npx, pnpm) and modification of local configuration files (e.g., CLAUDE.md, .cursorrules).
  • Sanitization: No explicit sanitization or validation of the content retrieved from external skill sources is specified in this entry skill.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 9, 2026, 11:20 AM
Security Audit — agent-trust-hub — tanstack-ai