sales-brief

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill performs standard business logic for sales analysis, ranking products by revenue and seasonality without any suspicious operations.
  • [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes data from external business tools. Analysis of the risk factors:
  • Ingestion points: External data is retrieved from ~~платежи (ЮKassa, Tinkoff), ~~бухгалтерия (1C, MoySklad), and ~~crm systems.
  • Boundary markers: While explicit data delimiters are absent, the skill includes a critical safety directive: "Never plan or publish content automatically," ensuring that output must be reviewed by a human.
  • Capability inventory: The skill has access to Bash, WebFetch, and Read tools.
  • Sanitization: No explicit sanitization or filtering of the ingested business data is performed prior to analysis.
  • [DATA_EXFILTRATION]: No evidence of unauthorized data transmission or credential harvesting was found. The skill's primary function is to summarize internal data for the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 01:59 AM
Security Audit — agent-trust-hub — sales-brief