The Agent Skills Directory

[DATA_EXFILTRATION]: The skill instructions direct the agent to access and read the .env file to extract configuration details like application ports. Accessing sensitive environment files is a high-risk activity as these files often contain secrets and credentials.
[REMOTE_CODE_EXECUTION]: The skill triggers the execution of npm install. This allows for the installation of arbitrary packages defined in a project's package.json, which could lead to remote code execution if the project dependencies are malicious or unpinned.
[COMMAND_EXECUTION]: The skill executes shell commands such as npm run build and npm run dev. These commands run user-defined scripts from the project configuration, which could be exploited to run malicious code on the host system.
[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from an external markdown file (tests/e2e-test-plan.md) to drive its testing logic. This creates a surface for indirect prompt injection where an attacker could embed malicious instructions within the test data.
Ingestion points: tests/e2e-test-plan.md
Boundary markers: Absent
Capability inventory: Shell command execution (npm), browser automation (Playwright), and file system access.
Sanitization: Absent

page-test