The Agent Skills Directory

[COMMAND_EXECUTION]: The helper script scripts/with_server.py facilitates the execution of arbitrary shell commands. It uses subprocess.Popen with shell=True to run commands passed via the --server argument, specifically to support shell features like directory changes (cd) and command chaining (&&). While this is functional for server management, it represents an execution surface for any strings passed to the script.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process data from external, potentially untrusted sources (web applications).
Ingestion points: The skill uses Playwright to capture page content (page.content()), screenshots, and console logs (page.on('console', ...)), all of which enter the agent's context.
Boundary markers: None identified; there are no explicit instructions to the agent to ignore instructions embedded in the web content.
Capability inventory: The agent has access to Bash, Read, and Write tools, and can execute scripts that interact with the local filesystem and network.
Sanitization: There is no evidence of filtering or sanitization of the captured DOM or console output before it is processed by the agent.
[EXTERNAL_DOWNLOADS]: The skill instructions include the installation of the playwright library and the Chromium browser runtime. These downloads target official, well-known registries and repositories.

webapp-testing