agent-next-js-expert
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides standard documentation and high-quality code examples for Next.js development. The examples demonstrate secure patterns, such as using Zod for input validation and checking authentication status in Server Actions.
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes the
$ARGUMENTSplaceholder to ingest user-specified tasks. While this represents a surface where untrusted data enters the agent's context, it is a standard design pattern for this type of agent skill. - Ingestion points: The
SKILL.mdfile contains the$ARGUMENTStag at the end of the instructions. - Boundary markers: Absent around the placeholder.
- Capability inventory: The skill is designed for a general-purpose agent, which typically possesses file-system and command-execution capabilities to perform development tasks.
- Sanitization: No explicit sanitization or filtering of the injected task content is defined within the skill itself; the skill relies on the underlying model's safety guardrails.
Audit Metadata