prompt-template-design
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is creating parameterized prompt templates, which creates an inherent surface for indirect prompt injection when processing external data.
- Ingestion points: Variable-based templates like 'LangChain PromptTemplate' and 'FewShotPromptTemplate' (SKILL.md).
- Boundary markers: The skill recommends 'Input validation rules' and 'Structured output instructions' to define template boundaries (SKILL.md).
- Capability inventory: The skill has access to tools including 'Bash', 'Read', 'Write', 'Edit', 'Glob', and 'Grep' (SKILL.md).
- Sanitization: Documentation notes 'Input validation rules' and 'Testing with edge cases' as implementation details and best practices (SKILL.md).
- [SAFE]: The skill depends on 'langchain-core', a standard library for building applications with large language models.
Audit Metadata