gmail
Pass
Audited by Gen Agent Trust Hub on Mar 29, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes the 'orth' command-line interface to execute various Gmail actions. This is a vendor-provided tool from orthogonal-sh and is used according to its documented functionality.
- [PROMPT_INJECTION]: The skill handles untrusted data from external sources, creating a surface for indirect prompt injection.
- Ingestion points: External email content is retrieved via the '/list-emails' and '/get-email' actions in SKILL.md.
- Boundary markers: There are no explicit delimiters or instructions provided to the agent to distinguish email content from system instructions.
- Capability inventory: The skill includes the ability to send emails and create drafts, which could be misused if the agent follows instructions found within an email.
- Sanitization: No sanitization or escaping of the ingested email data is specified in the instructions.
Audit Metadata