swiss-software-contracts
Pass
Audited by Gen Agent Trust Hub on Sep 30, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and analyze external data sources which could contain malicious instructions.
- Ingestion points: As defined in the 'Arbeitsweg' and 'Workflow' sections, the skill processes user-supplied documents such as 'Verwaltungsakte' (administrative acts), 'Vertragsurkunden' (contract documents), and 'Schriftsätze' (pleadings).
- Boundary markers: The instructions do not define clear delimiters (e.g., XML tags or triple quotes) or provide explicit warnings for the agent to ignore instructions embedded within the analyzed legal documents.
- Capability inventory: The skill performs text analysis and generates outputs like 'Memo, Matrix, Redline, oder Counsel-Briefing'. It does not explicitly define tool usage in the frontmatter, limiting the immediate risk of automated action execution.
- Sanitization: The skill lacks protocols for sanitizing or filtering input data before interpolation into the analysis prompt.
Audit Metadata