linkedin-ads-audit

Pass

Audited by Gen Agent Trust Hub on May 2, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes data from external LinkedIn Ads API endpoints, creating an indirect prompt injection surface.
  • Ingestion points: Campaign metadata and creative content are retrieved via the mcp__cogny__linkedin_ads__* tools.
  • Boundary markers: The instructions do not employ delimiters to isolate retrieved external data within the prompt.
  • Capability inventory: The agent environment has access to the Bash and Write tools.
  • Sanitization: There is no specific validation or escaping of the advertising data before it is analyzed.
Audit Metadata
Risk Level
SAFE
Analyzed
May 2, 2026, 06:44 AM
Security Audit — agent-trust-hub — linkedin-ads-audit