reviewing-cc-config

Pass

Audited by Gen Agent Trust Hub on Apr 14, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill utilizes a restricted bash command Bash(wc *) to calculate word counts for token estimation. This is limited to local configuration files and does not present a command injection risk in this context.
  • [DATA_EXFILTRATION]: No network tools (such as curl or wget) are included in the allowed-tools list. The skill reads local configuration files, including the global ~/.claude/CLAUDE.md, which is consistent with its stated purpose of auditing configuration quality.
  • [PROMPT_INJECTION]: The skill implements automated reviews using sub-agents. While it processes user-provided configuration files which could contain instructions, the primary agent maintains control of the workflow and any edits to the filesystem are gated by user confirmation or a specific command-line argument (--fix).
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 14, 2026, 08:41 PM