israeli-hon-declaration-preparer
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection because it facilitates the ingestion and analysis of untrusted external data sources provided by the user, such as financial demand letters and statements.
- Ingestion points: The workflow requires the agent to read and extract data from demand letters (Step 1), trade histories (Step 4), and previous declaration documents (Step 5).
- Boundary markers: The instructions do not define specific delimiters or security headers to prevent the agent from accidentally executing instructions that might be embedded within these processed files.
- Capability inventory: The skill recommends the integration of MCP servers (such as
asher,il-bank, andisraeli-bank) which have access to live financial data and account balances, increasing the potential impact of a successful injection. - Sanitization: There are no specified procedures for sanitizing or filtering the content of ingested PDF or image files before processing their text.
Audit Metadata