paper-preference-planner
Pass
Audited by Gen Agent Trust Hub on Aug 1, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No malicious patterns, obfuscation, or suspicious behaviors were detected. The skill is limited to processing text inputs and generating a formatted text output.\n- [PROMPT_INJECTION]: The skill processes untrusted user input via the
user_messagevariable. While this is a surface for indirect prompt injection, the skill lacks the system capabilities (shell access, network access, or file writes) required to exploit such an injection. The instructions also strictly constrain the output format, providing an additional layer of behavioral control.\n- [DATA_EXFILTRATION]: There are no indicators of data exfiltration. The skill does not access credentials, environment variables, or sensitive file paths, and it does not perform network operations.
Audit Metadata