skills/garethmanning/education-agent-skills/ai-facilitated-collaborative-learning-designer/Gen Agent Trust Hub
ai-facilitated-collaborative-learning-designer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a purely instructional template for designing educational activities. It contains no executable code, tool invocations, or network requests. All referenced academic sources are well-known in the field of learning sciences.
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-provided strings to generate its output. Ingestion points: Untrusted data enters via the
collaborative_taskandcollaboration_challengeplaceholders inSKILL.md. Boundary markers: No delimiters or warnings are present to distinguish user input from instructions. Capability inventory: None; the skill lacks subprocess calls, file-write operations, or network access. Sanitization: No validation or filtering is applied to the input. Due to the lack of exploitable capabilities, this represents a surface with no immediate security impact.
Audit Metadata