gmail-organize
Pass
Audited by Gen Agent Trust Hub on Sep 24, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill documentation provides legitimate commands for organizing Gmail (labeling, archiving, trashing). It promotes security best practices by instructing the agent to use
--dry-runand obtain explicit user confirmation before trashing or performing bulk modifications. - [INDIRECT_PROMPT_INJECTION]: The skill handles untrusted data from user emails.
- Ingestion points: Email identifiers and metadata fetched via
gmail search(SKILL.md). - Boundary markers: The instructions require the agent to show the operation count and check the set of IDs before execution, ensuring a human-in-the-loop verification step.
- Capability inventory: The CLI tool allows for message modification (
gmail modify) and label management (gmail label) (SKILL.md). - Sanitization: The skill uses IDs for operations, limiting the impact of malicious content within the emails themselves on the tool's execution flow.
Audit Metadata