Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes a local shell script
scripts/mail.shwhich wraps the system commandtmail. This is the intended primary purpose of the skill to facilitate communication within the agent environment. - [REMOTE_CODE_EXECUTION]: No remote code execution or external downloads were detected. The scripts are local and the tools are expected to be on the system PATH.
- [DATA_EXFILTRATION]: No data exfiltration patterns were detected. The skill interacts exclusively with the
TARIBOY_TOOLS_SOCKETand the localtmailcommand for internal messaging. - [PROMPT_INJECTION]: No attempts to override agent instructions or bypass safety filters were found in the instructions or metadata.
Audit Metadata