spark-recipe-multi-account-review
Pass
Audited by Gen Agent Trust Hub on Apr 30, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses the
sparkCLI tool to perform inbox management tasks such as listing accounts, folders, and filtering messages. These actions are consistent with the skill's stated purpose. - [SAFE]: The skill is explicitly limited to
read-onlyaccess in its metadata. The instructions focus on observation and summarization, avoiding any actions that could modify user data or account settings. - [SAFE]: No instances of prompt injection, obfuscation, hardcoded credentials, or unauthorized network operations were found in the skill content.
Audit Metadata