spark-recipe-label-organize
Pass
Audited by Gen Agent Trust Hub on May 8, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses the 'spark' CLI tool to perform standard email organization tasks such as labeling and moving messages. No malicious commands, exfiltration patterns, or obfuscation were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a surface for processing untrusted data from emails. While an attacker could attempt to embed instructions in an email to influence the agent's behavior, the skill's capabilities are restricted to organization actions (labels/folders), and such risks are common to email management workflows.
Audit Metadata