The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands to configure the local environment, search for browser executables (such as Chrome, Brave, or Edge) in the /Applications directory, and operate the playwright-cli and gh tools.
[DATA_EXFILTRATION]: To facilitate automated UI testing, the skill searches for development credentials, seed users, and login recipes in repository files like .env.example, AGENTS.md, and README. It captures visual snapshots of the application which are then uploaded to GitHub Pull Requests using the gh CLI tool as part of the intended workflow.
[INDIRECT_PROMPT_INJECTION]:
Ingestion points: The agent ingests and processes content from external web pages through the browser automation session (SKILL.md).
Boundary markers: No specific boundary markers or "ignore" instructions are implemented to protect the agent from potentially malicious instructions embedded in the target web content.
Capability inventory: The agent has the ability to interact with the page (clicking and filling forms) and exfiltrate data via screenshots to GitHub (SKILL.md).
Sanitization: There is no evidence of sanitization or filtering of the web content before it is processed by the agent.

browser