The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions define usage of the gws command-line utility for interacting with API resources such as messages, operations, and subscriptions.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to handle external data from Google Workspace events, creating a potential vector for indirect instructions.
Ingestion points: Data from Google Workspace event streams is ingested via methods like stream, get, and list in SKILL.md.
Boundary markers: No explicit markers or delimiters are provided in the instructions to separate untrusted external data from the agent's core logic.
Capability inventory: The skill allows execution of shell commands through the gws binary as documented in SKILL.md.
Sanitization: The instructions do not specify any validation or sanitization routines for the external data being processed.

gws-events