ag-se-boersennotiert-router
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill contains no executable code, scripts, or binary files. It consists entirely of markdown-based instructions for an AI agent's behavior.
- [INDIRECT_PROMPT_INJECTION]: The skill defines a workflow that ingests external data, such as documents and evidence provided by the user (referencing 'Dokumente und Beweismittel sammeln' in SKILL.md). While this creates an ingestion surface for potentially untrusted data, the skill lacks any high-risk capabilities—such as file writing, command execution, or network requests to arbitrary domains—that could be abused through this vector. No specific boundary markers or sanitization steps are defined for this input processing.
Audit Metadata