gate-info-web3

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

• Third-party content exposure detected (medium risk: 0.30). The workflow consumes community search results, social sentiment, UGC snippets, and web searches via gate-cli news commands, which ingest arbitrary outsider-authored free text.

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

• Potentially malicious external URL detected (medium risk: 0.30). The update scripts (update-skill.sh and update-skill.ps1) contain functional runtime dependency logic that fetches external content from arbitrary GitHub URLs (github.com/gate/gate-skills) to update or install skill files.