Skills
skills/kensaurus/cursor-kenji/webapp-testing/Gen Agent Trust Hub

webapp-testing

Warn

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The helper script scripts/with_server.py uses subprocess.Popen and subprocess.run with shell=True to execute commands provided as CLI arguments. This pattern is vulnerable to command injection if the input commands are untrusted or maliciously formed.
  • [COMMAND_EXECUTION]: The script scripts/with_server.py performs a dynamic import of the os module within a lambda function passed to Popen. While used for process management, dynamic imports can be leveraged to obscure malicious operations.
  • [PROMPT_INJECTION]: The skill implements a reconnaissance-then-action pattern that ingests DOM content and screenshots from web pages. This creates a surface for indirect prompt injection attacks.
  • Ingestion points: SKILL.md (usage of page.content() and page.screenshot() to identify selectors)
  • Boundary markers: Absent
  • Capability inventory: scripts/with_server.py (arbitrary shell command execution)
  • Sanitization: Absent
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 2, 2026, 06:13 PM
Security Audit — agent-trust-hub — webapp-testing