The Agent Skills Directory

[COMMAND_EXECUTION]: The helper script scripts/with_server.py executes shell commands to manage development servers and run testing scripts. It uses subprocess.Popen with shell=True to support common server startup patterns such as directory changes and command chaining. This functionality is consistent with the skill's purpose as a developer testing tool.
[PROMPT_INJECTION]: The skill workflow involves processing untrusted external data by inspecting the DOM and screenshots of web applications, which presents a surface for indirect prompt injection.
Ingestion points: External data enters the agent context through page.content(), page.locator().all(), and page.screenshot() as described in SKILL.md.
Boundary markers: There are no explicit instructions or delimiters used to warn the agent about potentially malicious instructions embedded in the content being tested.
Capability inventory: The skill has the capability to execute shell commands via scripts/with_server.py and run arbitrary Python Playwright scripts.
Sanitization: The skill does not perform sanitization or validation of the HTML or visual data retrieved from the web applications during inspection.

webapp-testing