openai-docs

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill defines an MCP tool pointing to an official OpenAI domain (https://developers.openai.com/mcp). This is a reference to a well-known service and is considered safe.
  • [INDIRECT_PROMPT_INJECTION]: The skill fetches and processes content from external OpenAI documentation sites. This introduces a surface for indirect prompt injection, though the risk is minimized by the restriction to official domains and the requirement to cite sources.
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform searches and fetch documentation through specialized tools; it does not request direct shell command execution or unauthorized file system access.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 06:54 AM
Security Audit — agent-trust-hub — openai-docs