The Agent Skills Directory

[COMMAND_EXECUTION]: The skill relies on the execution of the gws binary to perform its tasks. The instructions direct the agent to use gws slides commands to interact with resources like presentations and pages. This is the intended primary functionality of the skill.
[INDIRECT_PROMPT_INJECTION]: The skill has the capability to read untrusted data from external sources (Google Slides presentations) using the get method. This data could contain malicious instructions that the agent might inadvertently follow.
Ingestion points: The gws slides presentations get command retrieves presentation content which is then processed by the agent.
Boundary markers: There are no explicit boundary markers or delimiters defined in this file to separate external presentation content from the agent's core instructions.
Capability inventory: The skill has permissions to read, create, and update presentations through the gws CLI.
Sanitization: The instructions do not specify any validation, filtering, or sanitization of the content retrieved from presentations.

gws-slides