margin-analyzer
Pass
Audited by Gen Agent Trust Hub on Jun 18, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [SAFE]: The skill is a legitimate utility for small business analysis, providing guidance on handling data inconsistencies and regulatory transitions (reference/gotchas.md).\n- [PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it ingests untrusted data.\n
- Ingestion points: It reads data from manual CSV uploads (reference/csv-schema.md) and tool integrations (~~бухгалтерия, ~~платежи).\n
- Boundary markers: No specific delimiters or instructions to ignore embedded commands are defined for the agent during data ingestion.\n
- Capability inventory: The skill's actions are restricted to mathematical calculations and markdown report generation.\n
- Sanitization: The skill provides logic for cleaning numeric data formats (currency symbols, decimal points) but does not explicitly filter for natural language instructions in input fields.
Audit Metadata