The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses npx playwright test across multiple steps in SKILL.md to reproduce failures, capture traces, and verify fixes. This involves executing code within the local shell environment.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted input (a test file path) via the $ARGUMENTS variable and interpolates it directly into shell commands (e.g., npx playwright test <file>). There are no boundary markers or sanitization instructions provided to prevent the execution of malicious shell metacharacters if a user provides a crafted file path. The skill's primary capabilities include subprocess execution and local file access.

fix