Security audit
Security checks for vulnerabilities and agentic risk
This skill is a simple AI-text detector that sends user-provided text to a disclosed external GPTHumanizer API.
Install only if you are comfortable sending text to GPTHumanizer's external detection service. Do not submit secrets, private customer data, regulated records, or unpublished confidential material unless your organization has approved that service.
The README describes a text detection skill backed by the GPTHumanizer Detection API but does not clearly warn users that submitted text may be transmitted to an external third-party service. This creates a real privacy and data-handling risk because users may paste sensitive, unpublished, regulated, or confidential text under the assumption processing is local or self-contained.
The documented cURL example clearly performs an outbound POST to a remote domain, which is expected for this skill but still represents external transmission of user content. In the context of an AI-detection skill, that behavior is functionally necessary, yet it remains dangerous if users are not made aware that their input is being sent off-platform to a third party.
curl -X POST "https://detect.gpthumanizer.ai/api/detect_ai" \
The example instructs users to send arbitrary text content to a third-party API endpoint but does not disclose that the text leaves the local environment or warn against submitting sensitive data. This creates a real privacy and data-handling risk because users may paste confidential, proprietary, or regulated content into the request without informed consent.
No suspicious patterns detected.