The Agent Skills Directory

[COMMAND_EXECUTION]: The script scripts/with_server.py uses subprocess.Popen with shell=True to execute commands provided via the --server argument. It also uses subprocess.run to execute the main automation command. This design allows for arbitrary shell command execution, which is the intended functionality of the tool but represents a high-capability surface.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from web applications, creating a vulnerability surface where malicious content on a page could attempt to influence the agent's behavior.
Ingestion points: The agent is instructed to use Playwright's page.content(), page.locator().all(), and page.screenshot() to inspect rendered web pages (SKILL.md).
Boundary markers: There are no explicit instructions or delimiters provided to the agent to distinguish between the skill's instructions and the content retrieved from the web applications.
Capability inventory: The skill provides shell execution capabilities through scripts/with_server.py and encourages the agent to write and execute custom Python Playwright scripts.
Sanitization: No sanitization, filtering, or validation is performed on the data retrieved via Playwright before it is processed by the agent.
[DYNAMIC_EXECUTION]: The skill's primary workflow involves the agent dynamically writing and executing Python scripts using the Playwright library to automate browser interactions (SKILL.md).

webapp-testing