sales-brief
Pass
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external accounting, payment, and CRM systems, creating a surface for potential indirect prompt injection attacks if the source data contains malicious instructions.
- Ingestion points: Transaction records from
~~платежи(YuKassa, Tinkoff), revenue data from~~бухгалтерия(1C, MoySklad), and marketing logs from~~crm(identified in SKILL.md). - Boundary markers: Absent. The instructions do not specify the use of delimiters or specific warnings to ignore instructions embedded in the external data.
- Capability inventory: The skill configuration allows access to the
Bash,WebFetch, andReadtools. - Sanitization: Absent. There is no mention of filtering, escaping, or sanitizing the data retrieved from external tools before it is processed by the agent.
Audit Metadata