twitter-x

CRITICAL E005: Suspicious download URL detected in skill instructions.

• Suspicious download URL detected (high risk: 1.00). These URLs point to an untrusted/unknown domain (canifi.com) and explicitly instruct fetching and executing remote shell scripts (curl | bash / .sh links), a high-risk pattern that can deliver malware or exfiltrate credentials.

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

• Third-party content exposure detected (high risk: 0.90). The SKILL.md instructs the agent to navigate to twitter.com and to "Navigate to Notifications > Mentions" and "Review recent mentions" (Usage Examples / Authentication Flow), which means the agent will fetch and interpret user-generated content from Twitter/X that could carry untrusted instructions affecting replies and actions.

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

• Potentially malicious external URL detected (high risk: 0.90). The Quick Install and Setup instructions explicitly run remote scripts via curl | bash (https://canifi.com/skills/twitter-x/install.sh and https://canifi.com/install.sh), which fetch and execute external code as a required installation/runtime dependency for the skill.