ad-spend-guardrails
Pass
Audited by Gen Agent Trust Hub on Oct 26, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is to guide the agent through an interview process to derive financial metrics for advertising spend. It does not utilize any tools or execute shell commands.
- [SAFE]: Analysis of the instructions shows no evidence of prompt injection, obfuscation, or persistence mechanisms. All logic is transparent and focuses on financial modeling and policy design.
- [SAFE]: References to external skills (e.g., mbfinotti/advertising-skills) are within the vendor's own namespace and do not involve remote code execution or unauthorized package installation.
- [SAFE]: The skill does not access sensitive local files or directories, and it does not perform any network operations to external or untrusted domains.
Audit Metadata