software-mna-dd
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 process external legal documents, contracts, and evidence provided by the user. This creates a potential surface for indirect prompt injection if the ingested documents contain hidden instructions. However, the skill does not possess dangerous automated capabilities that could be abused by such an injection, and the behavior is inherent to the primary purpose of a due diligence tool.
- Ingestion points: 'Dokumente und Beweismittel sammeln und auf Lücken prüfen' (contracts, administrative acts, expert reports).
- Boundary markers: Not explicitly defined for external content.
- Capability inventory: No command execution, script generation, or network exfiltration capabilities are present in the skill.
- Sanitization: No specific sanitization or filtering logic is mentioned for processed documents.
Audit Metadata