pre-call-brief
Pass
Audited by Gen Agent Trust Hub on May 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill serves as a template for sales professionals to organize meeting prep and deal strategy. It includes internal constraints to ensure accuracy and limit the volume of discovery questions generated for the user.
- [PROMPT_INJECTION]: No malicious override or bypass instructions were found. The 'NEVER DO THESE' section contains legitimate operational constraints for the AI's output format and does not attempt to subvert system prompts.
- [DATA_EXFILTRATION]: No evidence of hardcoded credentials, sensitive file access (e.g., .ssh, .aws), or network exfiltration logic. The skill does not use any tools for external communication.
- [REMOTE_CODE_EXECUTION]: The skill consists entirely of markdown instructions and a JSON evaluation file; it contains no scripts, binaries, or commands for execution.
- [INDIRECT_PROMPT_INJECTION]: While the skill is designed to process external data (sales prospects, deal history), it lacks exploitable capabilities such as shell execution, file system writes, or network requests that could be leveraged by a malicious input.
Audit Metadata