The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of the gws CLI tool to interact with Google Chat API resources.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from Google Chat messages and metadata.
Ingestion points: Data enters the agent context through spaces, messages, and media resources defined in SKILL.md.
Boundary markers: The instructions lack explicit delimiters or safety prompts to ignore instructions within the ingested data.
Capability inventory: The agent can perform write and delete operations on chat spaces and messages.
Sanitization: No methods for sanitizing or filtering chat content are described.

gws-chat