The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/with_server.py utility uses subprocess.Popen with shell=True to execute server startup commands provided via the --server argument. It also uses subprocess.run to execute the final automation command. This behavior is the primary intended function of the tool for facilitating local development and testing workflows.
[SAFE]: The skill exhibits a surface for indirect prompt injection because it ingests and processes untrusted data from web pages and console logs. Evidence Chain: 1. Ingestion points: page.content(), page.locator().all() in examples/element_discovery.py, and page.on('console', ...) in examples/console_logging.py. 2. Boundary markers: Absent. 3. Capability inventory: subprocess.Popen and subprocess.run in scripts/with_server.py. 4. Sanitization: Absent. This risk is inherent to browser-based automation tasks and is considered acceptable within the context of the skill's stated purpose.

webapp-testing