israeli-fact-checker
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process external data, creating a potential surface for indirect prompt injection attacks.\n
- Ingestion points: The skill ingests user-provided claims and fetches content from external authoritative Israeli sources, including official government websites (cbs.gov.il, boi.org.il, data.gov.il) and specialized MCP tools, as detailed in SKILL.md.\n
- Boundary markers: The instructions do not define specific delimiters or "ignore" instructions to prevent the agent from following potentially malicious instructions embedded in the fetched web content.\n
- Capability inventory: The skill utilizes web fetching capabilities and multiple specialized MCP tools (e.g., budgetkey, knesset, israel-statistics) to retrieve and interact with external data in SKILL.md.\n
- Sanitization: The skill lacks explicit instructions for sanitizing, escaping, or filtering the raw content retrieved from external sources before it is analyzed by the agent.
Audit Metadata