The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes curl and jq to execute API requests and process responses. These operations are essential for the skill's functionality and are used as intended for document management.
[DATA_EXFILTRATION]: Network requests are directed to docs.googleapis.com. This communication is with a well-known service and is necessary for the primary purpose of reading and writing Google Docs content.
[PROMPT_INJECTION]: The skill reads external document content from Google Docs (SKILL.md), which serves as an ingestion point for untrusted data. While there are no specific sanitization steps or boundary markers defined, the risk of indirect prompt injection is a known factor when processing external documents, and the skill performs this action as part of its core utility.

google-docs