The Agent Skills Directory

[SAFE]: The skill serves as a technical instructional guide for library development and does not contain any malicious code, hidden instructions, or credential exposure.
[DATA_EXFILTRATION]: The skill uses gh and WebFetch to retrieve information from the official Pydantic AI repository on GitHub. These actions are limited to a well-known and trusted service/organization (GitHub/Pydantic) and are consistent with the skill's purpose for developers.
[INDIRECT_PROMPT_INJECTION]: The skill involves processing data from external sources such as pull request comments and SDK documentation. This is an intended design for its developer-centric functionality, and since the sources are restricted to the official project's trusted infrastructure, the risk of malicious injection is negligible.

adding-a-provider-api-feature