web-design-guidelines-3
Warn
Audited by Snyk on Feb 18, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.90). This skill explicitly uses WebFetch to retrieve and read guidelines from the public URL https://raw.githubusercontent.com/ZackKorman/skills/main/web-interface-guidelines/command.md and then applies those externally-fetched rules to user files, exposing the agent to untrusted third-party content that could contain indirect prompt-injection.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 1.00). The skill instructs at runtime to fetch and use the content of https://raw.githubusercontent.com/ZackKorman/skills/main/web-interface-guidelines/command.md as the authoritative rules and output-format instructions, so the remote file directly controls the agent's prompts/behavior.
Audit Metadata