openai-docs
Pass
Audited by Gen Agent Trust Hub on May 3, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill facilitates documentation retrieval from external sources using the Context7 MCP server. While it processes external data, it lacks dangerous capabilities (such as shell execution or network writing) that would make indirect prompt injection a significant risk.
- [EXTERNAL_DOWNLOADS]: The skill references the
@upstash/context7-mcppackage. This package is maintained by a well-known and reputable service provider, and its inclusion in configuration examples is standard for the skill's intended purpose. - [CREDENTIALS_UNSAFE]: Configuration examples for the MCP server correctly use placeholders and environment variable references rather than hardcoded secrets, promoting secure credential management practices.
- [SAFE]: No patterns of prompt injection, data exfiltration, or unauthorized persistence mechanisms were identified in the skill content.
Audit Metadata