tanstack-router
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements route loaders and components that ingest untrusted data from URL parameters (e.g.,
$postId). This creates a potential surface for indirect prompt injection if the processed data influences subsequent agent actions or is rendered without proper sanitization. - Ingestion points: Route parameters are accessed in
SKILL.mdandtemplates/route-examples.tsxvialoader: async ({ params }) => ...andRoute.useParams(). - Boundary markers: None present; there are no instructions or delimiters provided to the agent to treat these parameters as untrusted or to ignore instructions embedded within them.
- Capability inventory: The skill uses standard file system operations (Bash, Read, Write, Edit) for project scaffolding and package management (
bun add). - Sanitization: Code examples directly interpolate route parameters into fetch requests (e.g.,
fetch('/api/posts/${params.postId}')) without explicit validation or sanitization logic.
Audit Metadata