The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user input (regex patterns and test strings) to generate its analysis. While this is a known attack surface for indirect prompt injection, the skill has no dangerous capabilities such as file writes, network requests, or shell execution, making the risk negligible. The instructions specifically guide the agent to perform structured analysis rather than blindly following user-provided pattern content.
[SAFE]: No malicious patterns, obfuscation, or unauthorized data access commands were detected in the instructions or examples. The skill performs standard text-based utility functions within the expected scope of a regex debugger.

regex-debugger