skills/garethmanning/education-agent-skills/belonging-classroom-culture-designer/Gen Agent Trust Hub
belonging-classroom-culture-designer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill functions as a purely instructional prompt designed for educational support. It does not invoke any tools, perform network requests, or execute shell commands. The content is aligned with its stated purpose and relies on established psychological research.
- [INDIRECT_PROMPT_INJECTION]: The skill provides a surface for indirect prompt injection via the ingestion of user-provided classroom data. (1) Ingestion points: classroom_context and belonging_concern fields in SKILL.md. (2) Boundary markers: Input fields are labeled but lack strict delimiters. (3) Capability inventory: The skill has no access to tools or command execution. (4) Sanitization: No input filtering or escaping is implemented.
Audit Metadata