slack

Fail

Audited by Gen Agent Trust Hub on Feb 17, 2026

Risk Level: CRITICALREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONCREDENTIALS_UNSAFE
Full Analysis
  • REMOTE_CODE_EXECUTION (CRITICAL): The skill contains multiple instructions to execute remote scripts via curl -sSL [URL] | bash (specifically https://canifi.com/skills/slack/install.sh and https://canifi.com/install.sh). This is an extremely dangerous pattern that allows a non-trusted third party to execute arbitrary code on the host system without any validation or integrity checks.
  • EXTERNAL_DOWNLOADS (HIGH): The skill mandates downloading core components and setup utilities from canifi.com. Since this domain is not a recognized trusted source, the authenticity and safety of these downloads cannot be verified, posing a significant supply chain risk.
  • COMMAND_EXECUTION (MEDIUM): The installation process involves shell commands that modify the user's home directory (~/.canifi/skills/) and manipulate environment variables, which could be leveraged to establish persistence or exfiltrate data if the downloaded scripts are malicious.
  • CREDENTIALS_UNSAFE (LOW): The setup instructions encourage users to store sensitive credentials like SERVICE_PASSWORD in a local utility called canifi-env. This practice increases the risk of credential exposure if the environment manager or the underlying storage is not properly secured.
Recommendations
  • HIGH: Downloads and executes remote code from: https://canifi.com/skills/slack/install.sh, https://canifi.com/install.sh - DO NOT USE without thorough review
  • AI detected serious security threats
Audit Metadata
Risk Level
CRITICAL
Analyzed
Feb 17, 2026, 05:39 PM
Security Audit — agent-trust-hub — slack