research
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [COMMAND_EXECUTION] (SAFE): The skill references a local script
./scripts/research.shand providescurlexamples for interacting with the Tavily API. These commands are necessary for the skill's functionality and do not exhibit malicious intent such as privilege escalation or persistence. - [EXTERNAL_DOWNLOADS] (SAFE): The skill makes network requests to
api.tavily.com. While this domain is not on the global whitelist, it is the legitimate service provider for the skill's stated purpose of 'AI-synthesized research'. - [CREDENTIALS_UNSAFE] (SAFE): The skill instructs users on how to safely configure their own
TAVILY_API_KEYvia environment variables or a configuration file. No hardcoded API keys or secrets were found in the file. - [DATA_EXFILTRATION] (SAFE): There is no evidence of the skill attempting to access sensitive local files (like SSH keys or cloud credentials) or sending unauthorized data to external endpoints.
Audit Metadata