linkedin-ads-operator
Pass
Audited by Gen Agent Trust Hub on Oct 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill serves as a configuration template and instructional guide. It does not contain any executable scripts, shell commands, or obfuscated code blocks.
- [INDIRECT_PROMPT_INJECTION]: The skill defines tools such as
pull_linkedin_ads_performanceandpull_linkedin_company_engagementthat ingest data from external LinkedIn accounts. This creates a potential surface for indirect prompt injection if the source data contains malicious instructions. However, the skill provides a mitigation strategy by instructing the agent to follow an 'approve ≠ activate' workflow, ensuring human oversight for any proposed changes. - [DATA_EXFILTRATION]: No unauthorized data exfiltration patterns were detected. The skill uses standard OAuth-based access for LinkedIn Ads management as specified in the Synter MCP configuration.
- [COMMAND_EXECUTION]: No evidence of shell command execution or dynamic context injection was found in the documentation.
Audit Metadata