configure-ecc

Warn

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: MEDIUMEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONREMOTE_CODE_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill clones a remote repository from a third-party source (https://github.com/affaan-m/everything-claude-code.git) into the temporary /tmp directory. This source is not part of a recognized trusted vendor list.
  • [COMMAND_EXECUTION]: The installer executes several shell commands to manage files, including rm -rf, git clone, mkdir -p, and cp -r. It specifically modifies directories within the agent's sensitive configuration path (~/.claude/skills and ~/.claude/rules).
  • [REMOTE_CODE_EXECUTION]: The skill copies entire directories from the unverified remote source into the agent's skill directory. As noted in the instructions, these directories can contain scripts and configuration hooks (e.g., for continuous-learning-v2) that will be executed by the AI agent in future sessions.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Apr 1, 2026, 05:35 AM
Security Audit — agent-trust-hub — configure-ecc