learn-tech
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is primarily focused on prompt engineering for educational content delivery. It does not perform network operations, access sensitive system files, or execute external code.- [COMMAND_EXECUTION]: The skill instructs the agent to create a directory (learn-tech_outputs/) and save Markdown files. This is a legitimate use of file system capabilities for persistent storage of user-requested content and follows a predictable, non-sensitive path.- [PROMPT_INJECTION]: The skill processes arbitrary technical topics provided by users, which represents a potential surface for indirect prompt injection. However, the highly structured and rigid output template serves as an effective constraint that minimizes the likelihood of the agent executing instructions embedded within a topic name.
Audit Metadata