gog
Pass
Audited by Gen Agent Trust Hub on Mar 9, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill requires installing a binary from a third-party Homebrew tap (steipete/tap/gogcli), which is an external dependency from a source not on the trusted vendors list.
- [COMMAND_EXECUTION]: The skill executes the gog CLI to interact with Google Workspace APIs, including searching Gmail, reading Drive files, and modifying Sheets.
- [PROMPT_INJECTION]: The skill introduces a surface for indirect prompt injection due to its ability to ingest untrusted data and perform impactful actions.
- Ingestion points: Data is read from Gmail messages, Drive files, Sheets, and Docs (SKILL.md).
- Boundary markers: No markers are present to help the agent distinguish instructions from data.
- Capability inventory: The agent can send emails and update spreadsheets (SKILL.md).
- Sanitization: No content validation or sanitization is described in the skill definition.
Audit Metadata