building-pydantic-ai-agents

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill describes how agents ingest data from external sources via tool results, multimodal inputs, and mid-run message injection (RunContext.enqueue). It includes mandatory safety guidance warning developers that enqueued SystemPromptPart objects carry operator authority and should not be built from untrusted data (e.g., tool outputs or webhooks) to avoid load-bearing prompt injection attacks.
  • Ingestion points: untrusted data enters the agent context through Agent.run inputs, tool result payloads, and content enqueued during execution.
  • Capability inventory: Includes capabilities for WebSearch, WebFetch, CodeExecutionTool, and arbitrary function tools.
  • Boundary markers: Notes that enqueued system instructions are rendered with <system> tags on supported providers, distinguishing them from standard user content.
  • Sanitization: Recommends using the ProcessHistory capability to implement custom history trimming, PII removal, and summarization policies before data is sent to providers.
  • [COMMAND_EXECUTION]: Provides instructions for configuring the CodeExecutionTool, which utilizes provider-native sandboxed environments (such as OpenAI's code interpreter) for executing model-generated code.
  • [EXTERNAL_DOWNLOADS]: Documents integration patterns for well-known services and search providers including DuckDuckGo, Tavily, Exa, and Model Context Protocol (MCP) servers.
  • [SAFE]: Includes security best practices for observability, specifically cautioning against the use of full HTTP capture (capture_all=True) in production logging to prevent the accidental exposure of secrets, credentials, or sensitive prompt content in diagnostic telemetry.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 07:22 PM
Security Audit — agent-trust-hub — building-pydantic-ai-agents