The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill enables the agent to fetch and process content from Google Slides presentations, which is an external and untrusted data source.
Ingestion points: The presentations.get method is used to read existing presentation data into the agent's context (SKILL.md).
Boundary markers: The skill instructions do not specify any delimiters or instructions for the agent to ignore or isolate embedded instructions within the slide content.
Capability inventory: The skill has the capability to execute shell commands via the gws CLI tool to create, read, and update presentations.
Sanitization: There is no documentation or instruction for sanitizing, validating, or filtering the data retrieved from Google Slides before it is processed by the agent.

gws-slides