tanstack-router
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEPROMPT_INJECTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill uses authoritative language ("CRITICAL", "MUST", "Do not proceed") to direct the agent to fetch external documentation before providing answers. While this is an attempt to override the model's internal training data behavior, it is functionally intended to prevent API hallucinations and ensure accuracy using a well-known official source.
- [INDIRECT_PROMPT_INJECTION]: The skill creates a surface for indirect injection by instructing the agent to fetch and process live documentation from
tanstack.com. - Ingestion points: External documentation fetched via
WebFetchas instructed inSKILL.md. - Boundary markers: None; the skill does not specify delimiters for the fetched content.
- Capability inventory: None; the skill provides documentation and best practices without defining executable scripts or system-level tools.
- Sanitization: None; the skill does not specify sanitization or validation for the remote content.
Audit Metadata