run-campaign

Pass

Audited by Gen Agent Trust Hub on Jun 18, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from external sources including accounting systems, payment platforms, and CRM software to influence marketing strategy and campaign execution.
  • Ingestion points: Data is pulled from external connectors for accounting (~~бухгалтерии), payments (~~платежей), and CRM (~~crm).
  • Boundary markers: The skill does not define specific delimiters or instructions to ignore potential commands within the ingested data.
  • Capability inventory: The skill has access to tools like Bash and WebFetch, which could be misused if an injection were successful.
  • Sanitization: There are no instructions provided to sanitize or validate the external data before the agent processes it for content generation or audience segmentation.
Audit Metadata
Risk Level
SAFE
Analyzed
Jun 18, 2026, 01:59 AM
Security Audit — agent-trust-hub — run-campaign