json-to-pydantic
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted JSON data provided by the user (referenced in
SKILL.md). This constitutes an ingestion point for external content. However, because the skill's primary function is generating static code and it does not utilize sensitive tools (e.g., shell execution, file writing, or network access), the vulnerability surface for exploiting the agent is minimal. - [SAFE]: The skill follows established patterns for creating Pydantic data models. The referenced dependencies and examples are standard and non-malicious.
Audit Metadata