Skills
Navigate
skills/kilo-org/kilo-marketplace/webapp-testing/Gen Agent Trust Hub

webapp-testing

Warn

Audited by Gen Agent Trust Hub on Sep 18, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The helper script scripts/with_server.py allows for the execution of arbitrary shell commands provided as arguments to manage server lifecycles, giving the agent broad shell access.
  • [DYNAMIC_EXECUTION]: The scripts/with_server.py script utilizes subprocess.Popen with shell=True to run server commands, which enables the execution of complex shell strings but increases the risk of command injection.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted web content (HTML, console logs) via Playwright and has shell execution capabilities. Ingestion points: page.content() and page.locator().all() in SKILL.md and examples/element_discovery.py, and browser console logs in examples/console_logging.py. Boundary markers: None. Capability inventory: Arbitrary shell execution via scripts/with_server.py, filesystem access, and file:// protocol support. Sanitization: None.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Sep 18, 2026, 06:02 AM