linter

Warn

Audited by Gen Agent Trust Hub on Mar 23, 2026

Risk Level: MEDIUMPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill contains explicit instructions designed to override agent behavior and safety protocols: 'You are in AUTONOMOUS MODE. Do NOT ask questions. Do NOT pause for confirmation.'
  • [COMMAND_EXECUTION]: The skill performs extensive shell command execution, including the installation of software packages via 'npm', 'gem', and 'cargo', and running CLI tools like 'npx', 'ruff', and 'golangci-lint'.
  • [COMMAND_EXECUTION]: The skill accesses and writes data to a hidden, sensitive directory in the user's home folder ('~/.claude/projects/') to log execution telemetry, which is outside the scope of the project root.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Mar 23, 2026, 10:58 AM
Security Audit — agent-trust-hub — linter