riksdag-regering-mcp
Pass
Audited by Gen Agent Trust Hub on Apr 16, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill mentions the installation of the riksdag-regering-mcp package via the npm registry, which is the official distribution method for this tool.\n- [DATA_EXFILTRATION]: The skill is configured to connect to a remote HTTP MCP server hosted at riksdag-regering-ai.onrender.com for data retrieval.\n- [PROMPT_INJECTION]: The skill ingests untrusted content from external Swedish political documents (such as motions and speeches) which are then summarized or analyzed by the agent, creating a risk for indirect prompt injection.\n
- Ingestion points: External text is retrieved from government sources using tools like get_dokument_innehall and get_g0v_document_content.\n
- Boundary markers: The instructions do not specify the use of delimiters or ignore-instructions warnings to isolate external data from the prompt context.\n
- Capability inventory: The provided tools are limited to querying and summarizing data and do not include high-risk capabilities like arbitrary command execution.\n
- Sanitization: There are no documented mechanisms for filtering or sanitizing the content fetched from the external APIs.
Audit Metadata