visual-recon

CRITICAL E006: Malicious code pattern detected in skill scripts.

• Malicious code pattern detected (high risk: 1.00). The skill provides step-by-step reconnaissance guidance that explicitly directs finding and prioritizing admin/login panels and attempting default/unauthenticated access and config/file discovery — actions that enable unauthorized access and credential theft.

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

• Third-party content exposure detected (medium risk: 0.30). Visual Recon’s runtime workflow reads outsider-authored free text from target web pages by taking screenshots of user-provided subdomains/URLs (e.g., gowitness file -f alive_subs.txt and gowitness single -u "$url"), which includes whatever text is rendered on those sites.

MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).

• Potentially malicious external URL detected (high risk: 0.70). The skill's prerequisite directs users to fetch and install remote code with "go install github.com/sensepost/gowitness@latest", which downloads and builds code that will be executed as a required runtime dependency.