akzg-aktenauszug-bauleiter
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFENO_CODEINDIRECT_PROMPT_INJECTION
Full Analysis
- [NO_CODE]: The skill consists entirely of natural language instructions and does not contain any executable scripts, binaries, or configuration files.
- [SAFE]: References to external websites such as gesetze-im-internet.de, dejure.org, and openJur are to well-known, reputable legal databases used for verifying norms and case law.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process untrusted external data (e.g., case files, evidence, and documents).
- Ingestion points: Untrusted data enters the agent context through the analysis of "Material", "Unterlagen", and "Dokumente" mentioned in the Arbeitsweg and Fallweichen sections.
- Boundary markers: The skill does not define specific delimiters or instructions to ignore embedded commands within the processed documents.
- Capability inventory: No subprocess calls, network writes, or file system operations are present in the skill; it only generates text-based reports and templates.
- Sanitization: There is no mention of sanitization or filtering for the external content.
Audit Metadata