openai-agent-sdk-skill
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill provides instructions to install software packages from the NPM registry, including
@openai/agents,zod, and@modelcontextprotocol/server-filesystem.- [COMMAND_EXECUTION]: Includes shell commands for project initialization, environment configuration, and running MCP servers vianpx.- [REMOTE_CODE_EXECUTION]: Describes the use ofhostedMcpToolwhich connects to an external URL (https://gitmcp.io/openai/codex) to provide tool capabilities.- [DATA_EXFILTRATION]: Contains examples for retrieving agent context and handling API keys through environment variables.- [PROMPT_INJECTION]: Includes standard instructions (e.g., 'You are a helpful assistant'). Note that instructions recommend using 'gpt-5-nano', which does not correspond to a publicly known model.- [INDIRECT_PROMPT_INJECTION]: The skill documents agents that process untrusted user input, creating a potential attack surface. \n - Ingestion points: User messages and conversation history in
SKILL.md. \n - Boundary markers: Absent in code examples. \n
- Capability inventory: Sensitive tools such as
delete_fileandcodeInterpreterToolare defined inSKILL.md. \n - Sanitization: Documents the implementation of
InputGuardrailandOutputGuardrailcomponents to validate and filter content.
Audit Metadata