gemini-chat

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONCREDENTIALS_UNSAFEEXTERNAL_DOWNLOADS
Full Analysis
  • [Remote Code Execution] (HIGH): The skill contains instructions to execute remote code via curl -sSL https://canifi.com/skills/gemini-chat/install.sh | bash. Piped remote execution is a high-risk pattern that allows an untrusted third party to execute arbitrary commands on the host system without prior review.
  • [External Downloads] (HIGH): The skill relies on scripts hosted at canifi.com, which is not a trusted source according to security guidelines. This includes both the skill installer and the canifi-env setup utility.
  • [Credentials Unsafe] (HIGH): The documentation requests users to input sensitive information, including GOOGLE_EMAIL and SERVICE_PASSWORD, into the canifi-env tool. Since the tool itself is installed via an untrusted remote script, there is no guarantee that these credentials are kept local or secure.
  • [Command Execution] (HIGH): The installation process involves direct shell command execution of unverified scripts, providing a significant attack surface for persistence or privilege escalation.
Recommendations
  • HIGH: Downloads and executes remote code from: https://canifi.com/install.sh, https://canifi.com/skills/gemini-chat/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Feb 17, 2026, 05:35 PM
Security Audit — agent-trust-hub — gemini-chat