The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by reading external data from Google Slides presentations. Malicious instructions embedded within slides could potentially influence the agent's behavior during processing.
Ingestion points: Presentation data is retrieved using the presentations.get method in SKILL.md.
Boundary markers: The skill does not implement specific delimiters or 'ignore' instructions to separate presentation content from system commands.
Capability inventory: The skill has the capability to execute shell commands via the gws binary to perform API actions.
Sanitization: The skill does not describe any sanitization or validation processes for the data fetched from the Slides API.
[COMMAND_EXECUTION]: The skill executes the gws command-line utility to perform its core functions. This behavior is expected as it is a vendor-provided tool for managing Google Workspace resources.

gws-slides