verasic-github-env

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 0.70). The set includes a typosquatting domain (https://github.com.evil.com/owner/repo) and malformed URLs (https://} and http://}) that are high-risk indicators because they can be used to obscure or redirect to malicious downloads.

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow instructs the agent to execute source .cursor/skills/verasic-github-env/scripts/load-gh-env.sh, which then reads GH_* values from repo files like .github-agent.local / .env.local (outsider-authored free text), and exports them into the running process context used by the agent.

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

• Potentially malicious external URL detected (high risk: 1.00). I flagged https://raw.githubusercontent.com/Milkywayrules/verasic-skills/main/setup.sh because the README and setup-protocol explicitly recommend running curl -fsSL https://raw.githubusercontent.com/Milkywayrules/verasic-skills/main/setup.sh | bash, which fetches and immediately executes remote code during setup/install (a runtime/installation step that executes external code).