vercel-connect
Pass
Audited by Gen Agent Trust Hub on Jun 15, 2026
Risk Level: SAFEDATA_EXFILTRATIONCOMMAND_EXECUTIONPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
- [Credential Management]: The skill is designed to obtain and use sensitive OAuth and OIDC tokens for services like Slack and GitHub. While these are managed through Vercel's infrastructure, users should ensure tokens are handled securely in their environment to avoid exposure.
- [Command Execution]: The skill uses the
vercel connectCLI to manage connections. This is a standard part of the Vercel developer workflow and occurs within the user's authenticated session; however, users should review CLI output for unexpected prompts. - [External Communication]: The skill makes network requests to
api.vercel.com,slack.com, andgithub.com. These are well-known services required for the skill's integration features. - [Indirect Prompt Injection Surface]: Since the skill retrieves data from external APIs (such as Slack messages or GitHub repository content), it introduces a surface where malicious instructions embedded in that data could potentially influence agent behavior. Standard sanitization practices for external data are recommended.
Audit Metadata