agent-template
Pass
Audited by Gen Agent Trust Hub on Mar 25, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is a documentation and utility tool for creating agent templates. The operations described are consistent with the stated purpose and follow standard agent configuration practices.\n- [PROMPT_INJECTION]: The skill defines a surface for indirect prompt injection by using user-supplied input to generate agent instructions. This is a documented risk factor for template-based agents but is a standard feature of this skill's design.\n
- Ingestion points: User-provided name and purpose arguments in SKILL.md.\n
- Boundary markers: The generated content is placed within a standard markdown/YAML structure but lacks specific instruction isolation markers.\n
- Capability inventory: The skill is designed to write markdown files to the filesystem.\n
- Sanitization: The skill does not perform explicit sanitization of the user-provided purpose string.
Audit Metadata