migrating-agno-to-pydantic-ai
Pass
Audited by Gen Agent Trust Hub on Sep 19, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill content is entirely instructional and documentation-based, designed to assist developers in refactoring codebases. It does not include any executable scripts, shell commands, or obfuscated payloads.\n- [EXTERNAL_DOWNLOADS]: The skill references documentation and packages from docs.agno.com and pydantic.dev. These are official sources for the respective frameworks and are considered trusted for the context of this migration task.\n- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to analyze application source code, dependencies, and logs. While this involves processing external data, the skill provides defensive guidance, such as using sandboxes for untrusted execution and treating ingested context as non-executable data. Ingestion points include repository instructions and source code in SKILL.md. Boundary markers are absent for the agent's reading process but recommended for the migrated app. Capability inventory is limited to file reading. Sanitization is not explicitly implemented in the prompt instructions.
Audit Metadata