template-engine
Pass
Audited by Gen Agent Trust Hub on Sep 25, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to render templates using dynamic data, which creates a potential surface for indirect prompt injection or server-side template injection (SSTI).
- Ingestion points: Document templates and dynamic variable inputs (SKILL.md).
- Boundary markers: No specific delimiters are defined for isolating untrusted content.
- Capability inventory: The skill utilizes Jinja2 and Handlebars for dynamic rendering and logic evaluation.
- Sanitization: The skill contains a guideline to 'Always validate inputs before processing', which is a best practice for mitigating injection risks.
- [DYNAMIC_EXECUTION]: The skill performs runtime rendering of Jinja2 and Handlebars templates, which involves the dynamic evaluation of expressions and logical constructs.
- [EXTERNAL_DOWNLOADS]: The skill footer references the author's public repository for skill collections.
- Reference: Fetches context or metadata from the inbharatai/claude-skills GitHub repository.
Audit Metadata