tanstack-query

Pass

Audited by Gen Agent Trust Hub on Oct 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill fetches documentation in Markdown format from tanstack.com. These requests target official project documentation to provide context-aware answers to developer queries.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external content from TanStack's documentation pages.
  • Ingestion points: External content is retrieved using WebFetch within a research sub-agent triggered by the Task tool.
  • Boundary markers: The skill utilizes structured Markdown headers (e.g., ## Your Research Goal, ## Context) in its prompt templates to help the agent distinguish between operational instructions and retrieved data.
  • Capability inventory: The research sub-agent is explicitly configured with readonly: true, which restricts it from performing any file writes, state changes, or other high-privilege actions based on the content it reads.
  • Sanitization: The skill specifically instructs the agent to fetch from a list of known, official documentation paths on the tanstack.com domain.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 2, 2026, 11:37 PM