aktenvernichtung-kdvg-12
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is purely instructional and contains no executable code, remote dependencies, or hidden logic. It does not attempt to bypass security filters or exfiltrate data.- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow for processing user-provided information related to military service and conscientious objection. While this creates an ingestion surface for untrusted data, the skill has no access to tools or system commands that could be exploited via injection. It also explicitly warns against uploading sensitive data to untested systems.
Audit Metadata