skills/klotzkette/claude-fuer-deutsches-recht/kanzlei-urheber-rechtsprechungs-livecheck/Gen Agent Trust Hub
kanzlei-urheber-rechtsprechungs-livecheck
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to process and analyze external, user-provided data which could contain malicious instructions designed to influence the agent's output.
- Ingestion points: The skill explicitly collects external data in
SKILL.mdunder the 'Arbeitsweg' and 'Sofortstart' sections, including 'Originaldateien' (original files), 'Verträge' (contracts), 'Schriftsätze' (pleadings), 'Screenshots', and 'Plattformmeldungen' (platform notifications). - Boundary markers: The instructions do not define clear delimiters or use 'ignore embedded instructions' warnings for the data being processed.
- Capability inventory: The skill identifies tasks such as generating legal memos, risk matrices, and case documentation. It does not utilize dangerous capabilities like arbitrary code execution or automated network exfiltration.
- Sanitization: There are no instructions for the agent to sanitize or validate the content of the ingested evidence for potential injection attacks.
Audit Metadata