israeli-annual-reports
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill's primary function is to analyze external documents such as annual reports and regulatory filings from TASE/MAYA systems. This introduces a surface for indirect prompt injection where malicious instructions embedded in financial reports could attempt to override agent behavior.
- Ingestion points: Israeli corporate annual reports, MAYA filings, and IFRS financial statements accessed at runtime (e.g., via the suggested
tase-mcpserver). - Boundary markers: The instructions lack explicit delimitation or warnings to ignore instructions found within the analyzed documents.
- Capability inventory: Includes a local Python glossary script (
scripts/financial_parser.py) and utilizes standard agent tools for analysis. - Sanitization: No specific sanitization or filtering logic is provided for external content processing.
Audit Metadata