configure-ecc

Fail

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: HIGHEXTERNAL_DOWNLOADSREMOTE_CODE_EXECUTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill clones a remote repository from https://github.com/affaan-m/everything-claude-code.git into the local /tmp directory. This source is not associated with the skill's author or a recognized trusted organization.
  • [REMOTE_CODE_EXECUTION]: The skill facilitates the installation of third-party AI skills and rules from the cloned repository into the agent's active execution environment (~/.claude/skills/ and ~/.claude/rules/). In the context of AI agents, skills are executable instructions; loading them from an unverified external source is equivalent to executing untrusted code.
  • [COMMAND_EXECUTION]: The skill performs several potentially dangerous shell operations including recursive deletion (rm -rf), repository cloning (git clone), and recursive copying (cp -r) into system-level and project-level directories.
  • [DATA_EXFILTRATION]: While no direct exfiltration was detected, the installation process involves reading and modifying configuration files in the ~/.claude/ directory, which can contain sensitive project information or settings.
Recommendations
  • AI detected serious security threats
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 24, 2026, 07:43 AM
Security Audit — agent-trust-hub — configure-ecc