decision-shot
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill is purely instructional, providing a template and rules for the AI agent to format decision summaries. It does not include any scripts, binaries, or tool invocations.
- [SAFE]: No prompt injection or bypass attempts were detected. The instructions focus on output formatting and linguistic style (e.g., 'knappform' style).
- [SAFE]: No data exfiltration or sensitive file access patterns are present. The 'Vollanalyse' field is a placeholder for documentation references and does not automate data retrieval.
- [SAFE]: No obfuscation, dynamic execution, or persistence mechanisms were found. The 'session provenance' feature is a standard metadata stamping practice for documentation and does not pose a security risk.
Audit Metadata