skills/mukul975/anthropic-cybersecurity-skills/detecting-qr-code-phishing-with-email-security/Gen Agent Trust Hub
detecting-qr-code-phishing-with-email-security
Pass
Audited by Gen Agent Trust Hub on Apr 7, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill provides a functional toolset for cybersecurity analysis, specifically targeting QR code phishing detection in emails and images.
- [SAFE]: Python scripts (
agent.py,process.py) utilize well-known libraries such asPillowandpyzbarfor image processing and QR decoding. No suspicious command execution or dynamic code evaluation (eval/exec) patterns were found. - [SAFE]: Data ingestion is limited to reading local
.emland image files for analysis. The tool does not perform unauthorized network requests or exfiltrate sensitive data. - [SAFE]: API references in documentation use standard placeholders for credentials, and no hardcoded secrets were found in the source code.
- [SAFE]: While the skill processes untrusted input (emails/images), it does so via static regex analysis and library-based decoding rather than feeding raw content into a prompt for LLM execution, minimizing indirect prompt injection risks.
Audit Metadata