ad-research
Pass
Audited by Gen Agent Trust Hub on Jul 17, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill focuses on legitimate market research by accessing official ad libraries from well-known services including Meta, Google, and TikTok. All network activity is restricted to these public-facing transparency platforms.
- [DATA_EXFILTRATION]: While the skill communicates with external domains, it only targets official advertising repositories to retrieve public data. There is no evidence of sensitive local file access or unauthorized data transmission to untrusted third parties.
- [PROMPT_INJECTION]: The skill ingests untrusted data from the web (competitor ad copy). This represents a surface for indirect prompt injection; however, because the skill uses this data strictly for analysis and does not involve high-privilege tool execution based on that data, the risk is considered safe for the intended research purpose.
- [COMMAND_EXECUTION]: No suspicious system commands, privilege escalation attempts, or unauthorized shell executions were identified. The use of browser tools is confined to standard data navigation and extraction.
Audit Metadata