openai-researcher
Pass
Audited by Gen Agent Trust Hub on Apr 18, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill defines a behavioral persona and a theoretical research framework. It does not contain executable scripts, shell commands, or network operations that could pose a security risk.
- [EXTERNAL_DOWNLOADS]: The skill provides a URL for its own source code on GitHub (
github.com/theneoai/*) to facilitate installation on various AI platforms. These references are vendor-specific and used for legitimate configuration purposes. - [PROMPT_INJECTION]: No instructions were found that attempt to bypass safety filters, override system prompts, or extract sensitive information. The 'Precautionary Principle' and safety gates mentioned are part of the academic persona and promote safe AI practices.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys, tokens, or passwords were found within the skill files or metadata.
- [DATA_EXFILTRATION]: There are no patterns indicating the collection or transmission of user data to external servers.
Audit Metadata