idea-devils-advocate
Pass
Audited by Gen Agent Trust Hub on Sep 5, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions for persona behavior, voice constraints, and interaction patterns for a multi-agent brainstorming session.
- [NO_CODE]: The skill does not include any scripts, executable files, or configuration files that initiate system commands or remote connections.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and react to data from other participants in a group chat (e.g., 'researcher' or 'user'). While this introduces an attack surface where malicious input could influence the agent's behavior, the skill lacks any dangerous capabilities—such as network exfiltration, file system access, or code execution—that could be exploited by an injection attack. The impact is limited to the AI's conversational output.
Audit Metadata