tanstack-query-v5

Pass

Audited by Gen Agent Trust Hub on Sep 1, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill documents patterns for fetching data from diverse sources such as external APIs, local storage, and file systems. This establishes a potential ingestion surface for untrusted data, though the instructions are standard for the technology described.
  • Ingestion points: The 'Versatile queryFn Pattern' in SKILL.md demonstrates ingestion from fetchUser (network), localStorage.getItem (browser storage), and readFile (filesystem).
  • Boundary markers: The provided examples do not include specific delimiters or 'ignore instructions' markers for the ingested data.
  • Capability inventory: The skill outlines patterns for data fetching (useQuery), background refetching, and data mutation (useMutation).
  • Sanitization: There is no mention of sanitization or validation of the fetched data before it is processed or rendered.
  • [EXTERNAL_DOWNLOADS]: The skill references several standard Node.js libraries commonly used in the React ecosystem.
  • Evidence: References to @tanstack/react-query, @lukemorales/query-key-factory, nuqs, and ahooks are provided as standard architectural dependencies.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 1, 2026, 11:06 PM
Security Audit — agent-trust-hub — tanstack-query-v5