The Agent Skills Directory

[SAFE]: No malicious patterns, obfuscation, or sensitive data exposures were identified. All external references point to legitimate, well-known domains such as github.com, google.com, iana.org, and terraform.io.
[NO_CODE]: The skill is comprised entirely of Markdown documentation, YAML/JSON configuration files, and a text-based grammar file. No executable scripts or binary code are provided within the skill package.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and review user-provided API definitions. While this constitutes an ingestion surface, the skill lacks any high-risk capabilities (such as network access or file system write permissions) that could be exploited by an injection attack.

google-aip