AIKIDO-2026-511457
@composio/openai is vulnerable to Insertion of Sensitive Information into Log File
30
Low Risk
This Affects:
@composio/openaiTL;DR
The OpenAI Responses provider logs the full MCP server response to standard output with console.log inside wrapMcpServerResponse. That response contains each MCP server URL, and those URLs can embed authentication tokens or other secrets in their path. Applications that connect MCP servers through this provider leak the credential bearing URLs into stdout and any captured log output.
Who does this affect?
You are affected if you are using a version that falls within the vulnerable range and you connect MCP servers whose URLs contain authentication tokens or other secrets.
Background info
@composio/openai is vulnerable to Insertion of Sensitive Information into Log File in versions 0.1.36 - 0.12.1.
How to fix this
Upgrade the @composio/openai library to the patch version.
Are You Affected?
Connect your repositories to instantly see whether vulnerable or malicious packages exist in your codebase.
Free. No credit card required.
I consent to receiving marketing communications based on Aikido’s Privacy Policy.
SOC 2Compliant
ISO 27001CompliantISO 42001Compliant
FedRAMPImplementing© All Intel data is openly available and commercially licensed.