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
BashandWritetools. - Sanitization: There is no specific validation or escaping of the advertising data before it is analyzed.
Audit Metadata