Oathe Security Badge

oathe / scan / reports / caution

Is antonia-sz/jd-interview-prep safe?

Use with caution. antonia-sz/jd-interview-prep is not clearly unsafe, but the audit flagged risks to review before you install it. Oathe's behavioral security audit gave the jd-interview-prep skill by antonia-sz a trust score of 70/100 with 3 findings (1 critical, 1 high). Report updated

https://clawhub.ai/antonia-sz/jd-interview-prep

70
CAUTION

Is antonia-sz/jd-interview-prep safe to install?

This interview preparation skill contains significant data privacy risks by transmitting user resumes and job descriptions to external APIs without clear disclosure. While the core functionality appears legitimate, the undisclosed data sharing and configurable endpoints create substantial security concerns.

What security issues were found in antonia-sz/jd-interview-prep?

Category Scores

Prompt Injection 95/100 · 30%
Data Exfiltration 20/100 · 25%
Code Execution 75/100 · 20%
Clone Behavior 95/100 · 10%
Canary Integrity 100/100 · 10%
Behavioral Reasoning 30/100 · 5%

Findings (3)

CRITICAL Undisclosed External Data Transmission -70 ▶

The generate_questions.py script sends user-provided resume and job description data to external APIs (DeepSeek/OpenAI) without clear disclosure in the skill description. This exposes sensitive personal and professional information to third-party services.

Evidence: API_BASE = os.environ.get("OPENAI_API_BASE", "https://api.deepseek.com") and urllib.request.Request(f"{API_BASE}/chat/completions", data=payload)

HIGH Configurable API Endpoints -10 ▶

The skill allows API endpoints to be configured via environment variables (OPENAI_API_BASE, DEEPSEEK_API_KEY), which could be exploited to redirect sensitive user data to malicious servers.

Evidence: API_KEY = os.environ.get("OPENAI_API_KEY") or os.environ.get("DEEPSEEK_API_KEY", "") and API_BASE = os.environ.get("OPENAI_API_BASE", "https://api.deepseek.com")

MEDIUM Sensitive Data Processing Risk -70 ▶

The skill processes highly sensitive personal information (resumes, job applications) and could be used to build profiles of users' career information or job search activities without adequate privacy protections.

Evidence: prompt = build_prompt(jd, resume) containing up to 3000 characters of personal/professional data

Should I install antonia-sz/jd-interview-prep?

Oathe's verdict for antonia-sz/jd-interview-prep is CAUTION with a trust score of 70/100. Recommendation: Review before install.