agrar-einfuehrung-rechtsquellen
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 process external data, including user-provided facts and legal documents (e.g., 'Bescheide, Verträge, Auszüge'), which creates a surface for indirect prompt injection.
- Ingestion points:
SKILL.md(Sections 'Fallweichen' and 'Prüfraster' where the agent is instructed to work with provided material and documents). - Boundary markers: Absent; there are no specific instructions or delimiters provided to ensure the agent ignores potential malicious instructions embedded within the user-provided legal documents.
- Capability inventory: The skill does not possess high-risk capabilities such as network operations, file-system writing, or subprocess execution, significantly limiting the potential impact of an injection attack.
- Sanitization: No sanitization or validation logic is defined for the external text content processed by the skill.
Audit Metadata