awe-wonder-experience-designer
Pass
Audited by Gen Agent Trust Hub on Sep 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill's instructions, metadata, and prompt template were thoroughly analyzed and no malicious patterns, data exfiltration techniques, or unauthorized code executions were detected. The skill acts purely as a text generator for lesson designs.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a vulnerability surface by ingesting external data into the prompt. Ingestion points: The
lesson_contentandstudent_profilesfields inSKILL.mdare directly interpolated into the prompt. Boundary markers: The skill does not use delimiters or instructions to ignore potential commands embedded in the input data. Capability inventory: No capabilities (tools, filesystem access, or network operations) are available to the skill. Sanitization: No validation or escaping is applied to the input variables. Despite the lack of markers and sanitization, the absence of agent tools and system capabilities makes this surface non-exploitable for security attacks.
Audit Metadata