nextjs-app-router-patterns
Pass
Audited by Gen Agent Trust Hub on Sep 28, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONNO_CODE
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructions create an ingestion surface by directing the agent to read and process external files (specifically 'resources/implementation-playbook.md') and implicitly interact with user-provided project code. The lack of defined boundary markers or explicit sanitization instructions for this content creates a minor vulnerability to indirect instructions embedded in those sources.
- Ingestion points: Skill instructions to open and process 'resources/implementation-playbook.md' and the implicit processing of user-provided Next.js application code.
- Boundary markers: The instructions do not provide delimiters or safety directives to distinguish between instructions and data when reading these external files.
- Capability inventory: The agent is authorized to read local files as part of its core operation, which is triggered by the skill's directives.
- Sanitization: No instructions for validation, escaping, or filtering of the ingested content are present.
- [NO_CODE]: The skill consists entirely of instructional text and metadata within a single markdown file. No Python scripts, Node.js packages, shell commands, or binary executables are included in the analyzed content.
Audit Metadata