The Agent Skills Directory

[COMMAND_EXECUTION]: The scripts/with_server.py script facilitates the execution of shell commands provided as arguments to start development servers and run automation scripts. It utilizes subprocess.Popen with shell=True to support complex shell syntax (like directory changes and command chaining), which is a standard requirement for managing local development environments.
[INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it ingests untrusted data from external web applications.
Ingestion points: Data is collected from the DOM in examples/element_discovery.py and from browser console logs in examples/console_logging.py.
Boundary markers: No explicit markers or instructions to ignore embedded content were found in the scripts.
Capability inventory: The skill is capable of executing shell commands and writing files to the local system.
Sanitization: There is no evidence of sanitization or filtering of the external web content before it enters the agent's context.

webapp-debugger