The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses osascript to interface with the local Google Chrome application and execute arbitrary JavaScript code within the context of active browser tabs. This mechanism allows the agent to dynamically generate and run code to interact with web elements, fill forms, and trigger page events.
[DATA_EXFILTRATION]: Accesses highly sensitive data from authenticated browser sessions, including page content (innerText), active URLs, and window titles. By design, this exposes session-specific information (such as logins and private user data) to the agent context for processing.
[PROMPT_INJECTION]: The skill is inherently vulnerable to indirect prompt injection due to its processing of untrusted external web data.
Ingestion points: Extracts raw text from websites using execute active tab of front window javascript "document.body.innerText..." in SKILL.md.
Boundary markers: Absent. The skill does not employ delimiters or specific instructions to isolate web content from the agent's core instructions.
Capability inventory: Features extensive interaction capabilities via osascript shell commands and browser-level JavaScript execution.
Sanitization: No evidence of sanitization or validation of the retrieved web content before it is processed by the agent.

preauthenticated-chrome