skills/reason-machines/codex-skills/codex-chatgpt-control-bridge/Snyk

codex-chatgpt-control-bridge

Warn

Audited by Snyk on Sep 16, 2026

Risk Level: MEDIUM

Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

Third-party content exposure detected (low risk: 0.10). The skill integrates ChatGPT web sessions into Codex workflows, ingesting model-generated responses from an external web product into the agent context.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

Potentially malicious external URL detected (medium risk: 0.30). The skill instructs installation of an unofficial third-party package (adamallcock/codex-chatgpt-control via marketplace/npm/pip) without enforced cryptographic verification, constituting a medium-tier unofficial operational dependency.

Issues (2)

W011

MEDIUM

Third-party content exposure detected (indirect prompt injection risk).

W012

MEDIUM

Unverifiable external dependency detected (runtime URL that controls agent).

Audit Metadata

Risk Level

MEDIUM

Analyzed

Sep 16, 2026, 03:57 AM

Issues

2