swedish-political-system
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection (Category 8) because it retrieves and processes data from external SQL tables that could be manipulated to include malicious instructions.
- Ingestion points: Data is fetched from tables like assignment_data, vote_data, and sweden_political_party in the Riksdagsmonitor platform.
- Boundary markers: No explicit delimiters or instructions are used to distinguish between data and commands in the provided SQL or Python templates.
- Capability inventory: The skill utilizes SQL execution for data retrieval and Python for seat allocation logic.
- Sanitization: The skill does not implement validation or sanitization for the data retrieved from external sources before it is processed by the agent.
Audit Metadata