The Agent Skills Directory

[COMMAND_EXECUTION]: The skill facilitates the execution of shell commands through the scripts/with_server.py helper to manage the lifecycle of local development servers, such as starting frontend or backend services.
[PROMPT_INJECTION]: The skill contains an indirect prompt injection surface by design. 1. Ingestion points: The skill reads external data from web applications via page.content() and DOM locators. 2. Boundary markers: No explicit boundary markers or isolation instructions are provided for processed web content. 3. Capability inventory: The agent has the ability to execute shell commands and write files (screenshots). 4. Sanitization: There is no evidence of sanitization or validation of the ingested content.
[SAFE]: The identified behaviors are expected for a testing utility, and the skill originates from a trusted organization's repository, providing assurance regarding its intent.

webapp-testing