Security audit
Security checks for vulnerabilities and agentic risk
This is a documentation-only skill for PydanticAI dependency injection; its example network and credential use is disclosed and purpose-aligned, though users should handle secrets carefully.
Before installing, treat the code as a pattern reference. If adapting the examples, pass already configured clients where possible, keep API keys out of source code, and ensure any injected database or HTTP client is trusted and scoped to the task.
This markdown file includes sample code that performs an outbound HTTP request and sends a credential in the Authorization header. The surrounding skill description does not explicitly warn that dependency injection may involve network calls and secret-bearing clients, which is required for markdown content when behavior can affect privacy or system integrity.
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.
) -> dict:
"""Fetch weather data for a city."""
response = await ctx.deps.client.get(
f'https://api.weather.com/{city}',
headers={'Authorization': ctx.deps.api_key}
)
return response.json()
The documentation explicitly states 'Pass connections, not credentials' at L190, implying dependencies should contain initialized clients rather than secrets. However, the example dependency object includes api_key='secret' and the tool sends it as an authorization header, which contradicts that stated guidance rather than merely omitting detail.