voss-advisor
Pass
Audited by Gen Agent Trust Hub on Mar 15, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: No security threats detected. The skill consists of instructional Markdown files providing negotiation strategies and communication techniques without any malicious payloads.
- [NO_CODE]: The skill is purely instructional and does not contain any Python, Node.js, or shell scripts.
- [PROMPT_INJECTION]: No instructions were found that attempt to bypass AI safety filters, ignore prior instructions, or extract system prompts. The content remains focused on its stated purpose as a negotiation advisor.
- [DATA_EXFILTRATION]: No commands for accessing sensitive system files (e.g., SSH keys, credentials) or performing network requests to external domains were identified.
- [PROMPT_INJECTION]: While the skill is designed to process external communication data such as transcripts and emails (Mode A), it contains no executable code or automation capabilities that could be exploited via indirect prompt injection.
Audit Metadata