The Agent Skills Directory

[SAFE]: The skill interacts exclusively with official Google API endpoints (docs.googleapis.com). These are well-known services and are considered safe.
[SAFE]: Authentication is handled by the platform's credential provider using standard bearer tokens; no credentials or secrets are hardcoded in the skill code.
[SAFE]: No patterns of code obfuscation, unauthorized data exfiltration, or malicious command execution were found.
[PROMPT_INJECTION]: The skill processes external data by reading document content, which creates a surface for indirect prompt injection.
Ingestion points: The get action retrieves document body content via skill-router.json.
Boundary markers: The skill does not implement specific boundary markers or instructions to ignore content inside the document.
Capability inventory: The skill is limited to document management (create, read, update) and lacks high-privilege capabilities such as shell access or arbitrary network requests.
Sanitization: Input text and document content are passed to the API without additional sanitization filters.

documents