abmahnung-arbeitsrecht
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 process external, untrusted data to generate legal documents, which represents an attack surface for indirect instructions.\n
- Ingestion points: User-provided case facts (Sachverhalt), employment contracts (Arbeitsvertrag), and perspective/goals defined in the 'Eingaben' section of SKILL.md.\n
- Boundary markers: Absent; the instructions do not include specific delimiters or warnings to ignore embedded commands within the processed data.\n
- Capability inventory: The skill does not contain any scripts, command-line operations, or network tools; its capabilities are restricted to the agent's default text processing.\n
- Sanitization: Absent; there is no logic provided to filter or escape instructions embedded within the user-provided legal context.\n- [SAFE]: The skill directs the agent to verify legal information using official and well-known government and legal databases including gesetze-im-internet.de, dejure.org, and eur-lex.europa.eu in SKILL.md. These are recognized as trusted informational sources.
Audit Metadata