spark-recipe-label-organize
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from emails which could contain malicious instructions.
- Ingestion points: Email content is retrieved in SKILL.md using
spark searchandspark emails. - Boundary markers: No specific delimiters or instructions to ignore content within emails are defined in this recipe.
- Capability inventory: The skill has the ability to label and move emails via
spark action attachLabel,detachLabel, andmoveToFolder. - Sanitization: No explicit sanitization or validation of email content is performed before processing.
- [SAFE]: No malicious patterns such as credential theft, remote code execution, or obfuscation were detected. All operations are standard email management commands consistent with the skill's stated purpose.
Audit Metadata