concept-explainer
Pass
Audited by Gen Agent Trust Hub on Feb 16, 2026
Risk Level: LOWPROMPT_INJECTIONNO_CODE
Full Analysis
- [PROMPT_INJECTION] (LOW): The skill is designed to process user-supplied concepts, which presents a surface for indirect prompt injection. Ingestion points: User-provided concepts via triggers defined in SKILL.md. Boundary markers: None provided in the templates to isolate user data from agent instructions. Capability inventory: No dangerous capabilities such as file writing, network access, or command execution are present in the skill. Sanitization: No input sanitization or validation is implemented.
- [NO_CODE] (INFO): The skill consists entirely of Markdown instructions and documentation with no executable scripts, binaries, or configuration files.
Audit Metadata