next-skills
Pass
Audited by Gen Agent Trust Hub on Jul 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns or security vulnerabilities were identified in the analyzed files. The skill functions as an orchestration layer that does not execute arbitrary code or access sensitive data.
- [PROMPT_INJECTION]: The skill implements the Next Skills Protocol (NSP) which reads metadata from other skills to suggest follow-up actions. While this creates a data flow surface, it is secured by design through human-in-the-loop confirmation.
- Ingestion points: Reads the
next-skillsfront-matter list from the just-finished skill'sSKILL.md. - Boundary markers: Instructions are scoped to structured YAML metadata fields.
- Capability inventory: The skill is capable of activating other skills via their activation phrases.
- Sanitization: A mandatory human-in-the-loop step (
std:human.review@v1) is used to present options to the user, ensuring that no skill is auto-invoked without explicit caller consent.
Audit Metadata