openai-docs-skill
Pass
Audited by Gen Agent Trust Hub on Sep 15, 2026
Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [EXTERNAL_DOWNLOADS]: The skill fetches documentation content and API schemas from the OpenAI developer documentation MCP server at https://developers.openai.com/mcp.
- [COMMAND_EXECUTION]: The scripts/openai-docs-mcp.sh script executes curl and jq to interact with the documentation server and process JSON-RPC 2.0 payloads.
- [INDIRECT_PROMPT_INJECTION]: The skill ingests markdown and schema data from an external source, creating a potential surface for indirect prompt injection.
- Ingestion points: Untrusted data enters the agent context via the fetch, search, and openapi subcommands in scripts/openai-docs-mcp.sh.
- Boundary markers: No specific delimiters or instructions to ignore embedded content are applied to the fetched documentation.
- Capability inventory: The skill performs network operations via curl to the OpenAI developer domain and processes data using jq.
- Sanitization: The retrieved documentation content is not sanitized or escaped before being displayed to the agent.
Audit Metadata