building-pydantic-ai-agents
Pass
Audited by Gen Agent Trust Hub on Mar 26, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill uses official framework resources and documentation links exclusively. All external URLs trace back to the verified vendor infrastructure (pydantic.dev, logfire.pydantic.dev).
- [SAFE]: No obfuscation, persistence mechanisms, or unauthorized privilege escalation patterns were identified in the provided code snippets or instructions.
- [PROMPT_INJECTION]: Identifies an indirect prompt injection surface through the framework's support for declarative YAML/JSON configurations and instruction template strings.
- Ingestion points: Agent.from_file and Agent.from_spec in SKILL.md and COMMON-TASKS.md.
- Boundary markers: Not explicitly defined in documentation examples.
- Capability inventory: Framework capabilities include WebSearch, WebFetch, and custom function-calling tools.
- Sanitization: Not explicitly documented in the patterns; implementation is left to the developer.
Audit Metadata