emotional_companion
Pass
Audited by Gen Agent Trust Hub on Feb 15, 2026
Risk Level: LOW
Full Analysis
- [Prompt Injection] (SAFE): No instructions to bypass safety filters, ignore system rules, or extract system prompts were detected. The skill focuses solely on persona adoption.
- [Data Exposure & Exfiltration] (SAFE): No commands or scripts exist to access local files, environment variables, or external network endpoints.
- [Remote Code Execution] (SAFE): The skill does not include any dependency management files, download commands, or dynamic code execution patterns.
- [Indirect Prompt Injection] (INFO): While the skill is designed to process user input (emotional sharing), it lacks any functional capabilities such as shell access, file writing, or network communication that could be exploited via malicious data.
- [Obfuscation] (SAFE): No Base64, zero-width characters, or hidden Unicode markers were found in the file content.
Audit Metadata