Email Classifier
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill provides structural guidance for email organization and does not contain any malicious patterns, commands, or exfiltration vectors.
- [INDIRECT_PROMPT_INJECTION]: The skill identifies a potential attack surface by processing untrusted data (emails).
- Ingestion points: Email content supplied by the user as part of the prompt (SKILL.md).
- Boundary markers: None provided to isolate untrusted email content from instructions.
- Capability inventory: No executable tools, scripts, or capabilities are included or requested by this skill.
- Sanitization: No input sanitization or validation is implemented.
Audit Metadata