qr-code-generator

Pass

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • Indirect Prompt Injection (LOW): The skill processes untrusted input from users and external data sources which could be used to embed malicious instructions.
  • Ingestion points: Processes URL and label/caption text from user input, and data from CSV files during batch generation.
  • Boundary markers: The workflow mentions URL validation (scheme + domain) but lacks specific boundary markers or sanitization for caption labels which are reflected in the output.
  • Capability inventory: Executes local Python scripts (scripts/generate_qr.py, scripts/batch_generate.py) and performs file-write operations for PNG and SVG exports.
  • Sanitization: Includes basic URL validation, but no explicit sanitization for label text or CSV content is mentioned.
  • Command Execution (SAFE): The skill utilizes local Python scripts for its primary logic. No patterns indicating arbitrary command execution, shell spawning, or unsafe subprocess calls were found in the skill definition.
  • External Downloads (SAFE): No remote scripts, package installations (pip/npm), or external binary downloads are requested in the skill's workflow.
Audit Metadata
Risk Level
SAFE
Analyzed
Feb 17, 2026, 06:25 PM