aktienrueckkauf
Pass
Audited by Gen Agent Trust Hub on Sep 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function involves analyzing external documents such as contracts, administrative acts, and court records, which creates an ingestion surface for untrusted data. If these documents contain malicious instructions, they could potentially influence the agent's output or recommended next steps.
- Ingestion points: The 'Arbeitsweg' and 'Fachkern' sections in SKILL.md specify the collection and analysis of external documents (Verwaltungsakte, Vertragsurkunden, Schriftsätze).
- Boundary markers: The instructions do not define clear delimiters or warnings to help the agent distinguish between the content of the analyzed documents and its own operational instructions.
- Capability inventory: The skill is authorized to draft documents, provide legal assessments, and suggest the use of additional skills within the plugin context.
- Sanitization: There are no explicit instructions to sanitize or validate the content of the ingested files before processing.
Audit Metadata