gog
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the
gogCLI tool through a third-party Homebrew tap (steipete/tap/gogcli). While the developer is a known figure in the software community, this remains an external dependency outside of official platform registries. - [COMMAND_EXECUTION]: The skill relies on executing the
gogbinary to interact with Google services. This includes capabilities to send emails, modify spreadsheets, and create calendar events, which could be abused if the agent is misled by malicious input. - [INDIRECT_PROMPT_INJECTION]: The skill possesses a significant attack surface for indirect prompt injection as it retrieves and processes content from untrusted external sources.
- Ingestion points: Data is imported into the agent's session from Gmail (via
gog gmail search), Google Drive (gog drive search), and Google Docs (gog docs cat). - Boundary markers: The instructions do not specify any delimiters or safety prompts to prevent the agent from following instructions hidden within the emails or documents it reads.
- Capability inventory: The agent has write-access capabilities, such as sending emails (
gog gmail send), which could be triggered by instructions found in the ingested data. - Sanitization: The skill does not implement sanitization or validation of the content retrieved from Google Workspace before presenting it to the agent.
Audit Metadata