nextjs-middleware-generator
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill mandates that the agent read an external configuration file (
config/defaults.md) to adapt generation patterns, imports, and code examples, creating a vulnerability to malicious instructions embedded in that file. - Ingestion points: The
config/defaults.mdfile referenced inSKILL.md. - Boundary markers: Absent; there are no instructions for the agent to ignore embedded commands or to delimit the configuration data from active instructions.
- Capability inventory: The skill possesses code generation capabilities for TypeScript middleware.
- Sanitization: Absent; the agent is instructed to directly adapt patterns and code from the external source without validation or filtering.
Audit Metadata