aktenvorblatt-erstellen

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFENO_CODE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to process user-supplied legal case facts and documents (Ingestion points: User input in SKILL.md under 'Fallweichen' and 'Unterlagen'). It does not define specific delimiters or instructions to ignore potential injections within that data (Boundary markers: Absent). However, the skill does not utilize any tools for network communication, file system modification, or shell execution (Capability inventory: None). No explicit validation or escaping of the user data is described (Sanitization: Absent). While an injection surface exists, the lack of dangerous capabilities renders it safe.- [SAFE]: The skill consists exclusively of procedural instructions and formatting requirements for legal professionals. No obfuscation, data exfiltration patterns, or unauthorized access attempts were detected.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 08:01 AM