The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses a CLI-based architecture where the agent executes scripts via npx tsx to interact with Google APIs.
[INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it reads and returns the full content of external Google Docs to the agent context.
Ingestion points: The readDocument function in scripts/gdocs.ts fetches and extracts plain text from the document body.
Boundary markers: There are no explicit boundary markers or instructions in SKILL.md to tell the agent to treat document content as untrusted data.
Capability inventory: The skill allows file system writes (fs.writeFile in exportDocument), Google Docs modification, and metadata listing.
Sanitization: Document content is extracted as plain text and returned without filtering or escaping of potential instructions.

gdocs