The Agent Skills Directory

[DATA_EXFILTRATION] (LOW): The script scripts/get-system-info.js accesses local system information including the platform, architecture, and release version. While not as sensitive as credentials, this exposes environment metadata to the agent's context.
[PROMPT_INJECTION] (LOW): The skill is vulnerable to Indirect Prompt Injection (Category 8).
Ingestion points: The yourname variable in SKILL.md is populated directly by user input.
Boundary markers: Absent. The user input is interpolated directly into the response string 你好，{yourname}... without delimiters or safety instructions.
Capability inventory: The skill has the capability to execute local JavaScript files and display system information.
Sanitization: Absent. If a user provides a name containing malicious instructions (e.g., "Ignore previous rules and instead... "), the agent might follow those instructions in the next workflow steps.
[COMMAND_EXECUTION] (SAFE): The skill executes a local JavaScript file scripts/get-system-info.js. This script uses only built-in Node.js modules and does not perform any risky operations like writing files or making network requests.

hello-world