The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches and refreshes OAuth tokens from the backend service at google-workspace-extension.geminicli.com during authentication.
[DATA_EXFILTRATION]: The skill performs network operations to official Google API endpoints (slides.googleapis.com and www.googleapis.com) to manage presentation data, and to google-workspace-extension.geminicli.com for OAuth token management.
[INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface for indirect prompt injection as it processes content from external presentations.
Ingestion points: The get-text command in scripts/slides.py extracts all text content from presentation slides, including text boxes and tables.
Boundary markers: The skill does not use specific delimiters or instructions to the agent to distinguish extracted presentation content from system instructions.
Capability inventory: The skill includes capabilities to perform network requests and modify Google Slides content via the batch-update, create, and replace-text commands.
Sanitization: No sanitization or filtering is applied to the extracted text before it is returned to the agent's context.

google-slides