The Agent Skills Directory

[CREDENTIALS_UNSAFE]: The skill is specifically designed to read and load Playwright storageState files (.playwright/profiles/*.json). These files contain highly sensitive authentication information, including active session cookies and localStorage tokens, which are treated as live credentials.
[COMMAND_EXECUTION]: The skill constructs and executes Bash commands via the playwright-cli using placeholders such as {session}, <role-name>, <origin>, and <name>. If these parameters are populated with unsanitized data containing shell metacharacters, it could lead to arbitrary command injection.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection by ingesting and acting upon untrusted data.
Ingestion points: Project configuration files (.playwright/profiles.json) and output from playwright-cli snapshot (representing live browser content).
Boundary markers: Absent; the skill does not define delimiters or provide instructions to ignore potentially malicious content within the ingested data.
Capability inventory: Subprocess calls via playwright-cli for navigating the browser, loading state, and modifying storage.
Sanitization: None; data extracted from the profile configuration and browser output is used directly to determine agent actions and populate command arguments.

use-profiles