email-composer
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [Prompt Injection] (SAFE): No instructions found that attempt to override system safety or bypass AI constraints.
- [Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network operations detected.
- [Dependencies & Remote Code Execution] (SAFE): No external packages or remote scripts are downloaded or executed.
- [Persistence & Privilege Escalation] (SAFE): No commands found that attempt to gain elevated privileges or maintain persistent access.
- [Indirect Prompt Injection] (LOW): The skill processes user-provided context to generate emails, creating a surface for indirect prompt injection. However, because the skill has no functional capabilities (network access, file writing, or command execution), the risk is negligible.
- [Obfuscation] (SAFE): No encoded strings, zero-width characters, or hidden content detected.
Audit Metadata