gdocs
Pass
Audited by Gen Agent Trust Hub on Mar 2, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
gogCLI to perform operations on Google Docs and Drive. It includes commands with high-impact capabilities such asgog drive delete <fileId> --forceandgog docs write <docId> --replace, which could result in data loss if the agent is manipulated into executing them. - [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it ingests data from external Google Docs without safety boundaries. Ingestion points: Document content is read into the agent's context using
gog docs cat. Boundary markers: No markers or instructions are provided to the agent to isolate the document content from its execution logic. Capability inventory: The agent has the power to delete files, overwrite documents, and move files within Google Drive. Sanitization: No sanitization or validation is performed on the content retrieved from documents before it is processed.
Audit Metadata