license-scanner-remediation
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 process untrusted external data, which creates a potential surface for indirect prompt injection attacks.
- Ingestion points: The instructions specify analyzing external content including software scanner outputs ("Scannerfunde"), contract documents ("Vertragsurkunden"), and administrative or legal filings ("Verwaltungsakte", "Schriftsätze", "Bescheide") mentioned in the
ArbeitswegandFachkernsections. - Boundary markers: The skill lacks explicit delimiters (e.g., XML tags or triple quotes) or negative constraints instructing the agent to ignore instructions that might be embedded within the analyzed legal or technical documents.
- Capability inventory: The analysis does not identify any dangerous tools or commands; the skill does not attempt to write to the file system, execute shell commands, or perform network operations (other than referencing well-known legal databases for research).
- Sanitization: There are no instructions for the agent to sanitize, escape, or filter content from external sources before processing it.
Audit Metadata