openai-ads-api
Pass
Audited by Gen Agent Trust Hub on Nov 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill follows security best practices for credential handling, explicitly instructing the agent to resolve API keys from environment variables or a local config file (
~/.config/openai-ads/token) with restricted permissions (chmod 600), and forbids printing or storing secrets in code or output. - [SAFE]: The skill implements strong operational guardrails, requiring explicit user authorization for spending actions (activation), irreversible actions (archiving), and budget increases. It also mandates identity verification (
GET /ad_account) before any mutation to ensure the correct account is targeted. - [EXTERNAL_DOWNLOADS]: The skill references official OpenAI documentation and API endpoints (
api.ads.openai.com,developers.openai.com). These are well-known, trusted services and do not pose a security risk. - [COMMAND_EXECUTION]: The skill uses standard shell commands (
curl,chmod,mkdir,read) for credential setup and API interaction. These are used in a documented, secure manner for local environment configuration.
Audit Metadata