The Agent Skills Directory

[SAFE]: The skill's instructions are focused on defensive security practices, such as using textContent over innerHTML, implementing Content Security Policy (CSP), and utilizing sanitization libraries like DOMPurify. No malicious patterns, hardcoded credentials, or unauthorized network operations were detected.
[INDIRECT_PROMPT_INJECTION]: The skill is designed to process and sanitize user-provided content, which inherently involves an attack surface for indirect prompt injection if malicious instructions are embedded within the data the agent is asked to analyze.
Ingestion points: User-provided code snippets, HTML content, or examples of user-generated data processed during security reviews or implementation tasks.
Boundary markers: Not explicitly defined in the instruction set, although the role focuses on identifying and neutralising malicious patterns in data.
Capability inventory: The agent provides coding advice and configurations but does not possess tool-based capabilities for direct execution, file writing, or network communication.
Sanitization: The instructions mandate the use of allowlist validation, DOMPurify, and context-aware encoding to handle untrusted data safely.

frontend-security-coder