The Agent Skills Directory

[SAFE]: No malicious patterns or unauthorized behaviors were detected. The skill facilitates standard operations for Google Sites through an established CLI tool provided by the vendor.
[PROMPT_INJECTION]: The skill identifies an indirect prompt injection surface when processing external data. Ingestion points: External content is retrieved using get, list, and search commands as defined in SKILL.md. Boundary markers: Present; guidelines explicitly instruct the agent to use the --wrap-untrusted flag. Capability inventory: The tool provides read and search access to site metadata and content. Sanitization: Present; the --wrap-untrusted flag is required to handle data from potentially untrusted sources.

gog-sites