The Agent Skills Directory

[COMMAND_EXECUTION]: The helper script scripts/with_server.py utilizes subprocess.Popen with shell=True to execute arbitrary strings provided as command-line arguments. This allows the execution of arbitrary shell commands, which is a high-privilege operation.
[PROMPT_INJECTION]: The skill is designed to ingest and process data from web applications (via page.content(), screenshots, and DOM inspection). This exposes the agent to indirect prompt injection if the processed web content contains instructions intended to override agent behavior.
Ingestion points: Web content is ingested in examples/element_discovery.py and recommended patterns in SKILL.md using page.content(), page.locator(), and page.screenshot().
Boundary markers: No specific delimiters or instructions to ignore embedded content are provided when processing web data.
Capability inventory: The skill can execute shell commands via scripts/with_server.py and write files to the local system as seen in examples/console_logging.py.
Sanitization: There is no evidence of sanitization or filtering of the content retrieved from web applications before it is processed by the agent.

webapp-testing