The Agent Skills Directory

Prompt Injection (LOW): The skill is vulnerable to indirect prompt injection through document content ingestion. \n
Ingestion points: The get-text command in scripts/docs.py retrieves content from Google Docs based on document IDs or URLs provided to the agent. \n
Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the skill's documentation or operational instructions. \n
Capability inventory: The skill allows the agent to create new documents, search through document titles, and modify existing content via append-text, insert-text, and replace-text. \n
Sanitization: There is no indication that the skill performs any sanitization or filtering of the document text before it is returned to the agent's context.

google-docs