tanstack-query-best-practices
Pass
Audited by Gen Agent Trust Hub on Sep 27, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists of markdown-based documentation and reference materials centered on TanStack Query. A thorough review of all instructions, evaluation prompts, and technical references found no evidence of prompt injection, data exfiltration, obfuscation, or persistence mechanisms.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and review user-provided code snippets, which constitutes an ingestion surface for untrusted data. However, the skill does not request or use any tools, network access, or file-writing capabilities. Consequently, there is no mechanism for injected instructions to compromise the environment. The assessment follows the mandatory evidence chain:
- Ingestion points: User-supplied code blocks in the conversation context (e.g., React/Vue/Angular snippets for review).
- Boundary markers: None explicitly defined, though code blocks in prompts serve as natural delimiters.
- Capability inventory: No tools, subprocess calls, or network operations are enabled or used by the skill.
- Sanitization: Not applicable as the skill performs no automated execution or downstream data processing beyond text analysis.
Audit Metadata