skills/garethmanning/education-agent-skills/historical-thinking-assessment-designer/Gen Agent Trust Hub
historical-thinking-assessment-designer
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's functionality is limited to prompt engineering for educational content generation. It does not perform network operations, access the file system, or execute code.
- [PROMPT_INJECTION]: Analysis of the instructions and prompt template found no evidence of bypass markers, jailbreak attempts, or instructions intended to override agent safety protocols.
- [DATA_EXFILTRATION]: No patterns associated with data exposure or exfiltration were identified. The skill does not access sensitive paths or use network tools like curl or wget.
- [REMOTE_CODE_EXECUTION]: The skill does not include any external dependencies, package installations, or remote script execution patterns.
- [INDIRECT_PROMPT_INJECTION]: While the skill interpolates user input (e.g., student level, historical topic) into its prompt, it lacks any dangerous capabilities (such as shell access or file writing) that could be exploited through malicious input. The risk is negligible as it only generates text for a teacher's review.
Audit Metadata