webapp-testing

Warn

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • COMMAND_EXECUTION (MEDIUM): The script scripts/with_server.py uses subprocess.Popen with shell=True to execute server commands provided via the --server argument. This allows for arbitrary shell command execution with the privileges of the agent process.
  • DYNAMIC_EXECUTION (MEDIUM): The skill's primary workflow involves the AI agent writing and executing 'native Python Playwright scripts' at runtime. While necessary for the skill's purpose, this represents a capability for arbitrary code execution.
  • INDIRECT_PROMPT_INJECTION (LOW): The skill instructs the agent to ingest untrusted data (DOM content, console logs) from web applications to identify selectors and determine its next actions. This creates a vulnerability where a malicious web page could influence the agent's behavior.
  • Ingestion points: page.content(), page.locator().all(), and console logs captured in examples/console_logging.py.
  • Boundary markers: None. The instructions do not specify any delimiters or warnings to ignore instructions found within the web page content.
  • Capability inventory: Arbitrary shell execution via scripts/with_server.py and arbitrary Python execution through script generation.
  • Sanitization: None. The agent is encouraged to use discovered content directly to formulate scripts and commands.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 17, 2026, 06:33 PM