ClawHub

Pydantic Ai Agent Creation

v1.0.0

Create PydanticAI agents with type-safe dependencies, structured outputs, and proper configuration. Use when building AI agents, creating chat systems, or in...

⭐ 0· 111·1 current·1 all-time
byKevin Anderson@anderskev
MIT-0
Download zip
LicenseMIT-0 · Free to use, modify, and redistribute. No attribution required.
Security Scan
VirusTotalVirusTotal
Benign
View report →
OpenClawOpenClaw
Benign
high confidence
✓
Purpose & Capability
The name/description (creating PydanticAI agents) matches the SKILL.md content: code examples, configuration, and patterns for typed agents. It references external model providers (OpenAI, Anthropic, Google, etc.) but does not request unrelated capabilities or secrets in the manifest.
✓
Instruction Scope
All runtime instructions are code examples and guidance for constructing agents and validation flows. The document does not instruct the agent to read local files, environment secrets, or send data to unexpected endpoints; it stays within the stated purpose.
✓
Install Mechanism
There is no install spec and no code files to be written or executed. This is instruction-only, so nothing will be downloaded or installed by the skill itself.
✓
Credentials
The skill declares no required environment variables or credentials. It references external model providers (which, when you run code based on these instructions, will require provider API keys), but the skill itself does not request or collect unrelated secrets.
✓
Persistence & Privilege
Flags indicate normal, non-persistent behavior (always: false). The skill does not request elevated or permanent presence and does not modify other skills or system-wide settings.
Assessment
This skill is a documentation/instruction bundle (no code installed) and appears coherent with its purpose. Before using the provided examples you will need to supply appropriate model provider credentials (OpenAI/Anthropic/Google/etc.) in your runtime environment — those are not requested by the skill manifest. When you run agent code in your environment: (1) keep provider API keys limited to the least privilege and store them in secure places (not hard-coded), (2) be mindful that enabling instrumentation or logging can expose prompts, deps (which may contain secrets) and model outputs to logs/telemetry, and (3) only connect the agent to trusted external services. If you want a stricter review, provide runtime code that will be used in your environment (or any files that perform network calls or logging) so I can check for accidental secret exfiltration or excessive logging.

Like a lobster shell, security has layers — review code before you run it.

latestvk97f4n3hcxg93gys8bxp5gq07s8395m2

License

MIT-0
Free to use, modify, and redistribute. No attribution required.
Termshttps://spdx.org/licenses/MIT-0.html

Comments