legislative-monitoring
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface due to its data-processing capabilities.\n
- Ingestion points: The skill ingests legislative text and metadata from multiple database sources, including 'view_riksdagen_committee_document' and 'document_content'.\n
- Boundary markers: There are no explicit delimiters or specific instructions to ignore instructions embedded within the ingested parliamentary text.\n
- Capability inventory: The skill uses SQL, Java, and Python (including scikit-learn and pandas) for sophisticated data analysis and predictive modeling; however, it does not demonstrate unauthorized file-system or network access.\n
- Sanitization: No explicit sanitization, input validation, or filtering of the external legislative content is present in the provided analytical code.
Audit Metadata