The Agent Skills Directory

[SAFE]: A thorough security analysis of the skill instructions and reference documents shows no signs of malicious intent or technical vulnerabilities. The persona is well-defined and constrained to design critique tasks. No evidence of prompt injection, data exfiltration, or obfuscation was found. While the skill possesses an attack surface for indirect prompt injection via the WebFetch and WebSearch tools, the lack of dangerous capabilities such as file-writing or code execution significantly limits the risk, and no exploitable logic was observed in the skill's specific instructions.

design-critic