abmahnung-reagieren
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external content such as legal warning letters (Abmahnungen) and General Terms and Conditions (AGB) provided by the user.
- Ingestion points: User-provided legal documents and contract clauses are processed to identify legal risks (SKILL.md).
- Boundary markers: The skill does not define explicit delimiters or instructions to ignore embedded commands within the analyzed legal text.
- Capability inventory: The skill does not utilize dangerous tools, shell execution, or network exfiltration capabilities in the analyzed file.
- Sanitization: There is no evidence of specific sanitization or escaping of the external text before it is processed by the agent.
Audit Metadata