tanstack-start-routing
Pass
Audited by Gen Agent Trust Hub on Sep 1, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill instructions focus on standard software development practices for the TanStack Start framework. The identified capabilities are consistent with the skill's stated purpose.
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to ingest external data which creates a potential attack surface.
- Ingestion points: Reads local documentation file (../../docs/routing-and-data.md) and project source route files.
- Boundary markers: No explicit delimiters or warnings to ignore instructions inside the ingested data are present.
- Capability inventory: The skill specifies the capability to run shell commands for 'route-tree generation' and 'typecheck'.
- Sanitization: No evidence of input sanitization or validation of the files being read.
- Note: This risk is inherent to tools that analyze source code and is considered acceptable for the intended use case.
- [COMMAND_EXECUTION]: The skill mentions running 'route-tree generation' and 'typecheck' as part of the verification process. These are standard development operations for the TanStack framework and do not involve untrusted remote sources.
Audit Metadata