writing-style

Pass

Audited by Gen Agent Trust Hub on Aug 26, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a shell wrapper (run.sh) to execute a local Python CLI (writing_style.py). This is the primary mechanism for managing output templates and applying them to local provider configuration files (e.g., ~/.claude/CLAUDE.md). The execution is limited to local file system operations and does not involve untrusted input or remote code.
  • [DATA_EXPOSURE]: The skill accesses several sensitive file paths, including ~/.claude/CLAUDE.md, ~/.codex/AGENTS.md, and ~/.gemini/GEMINI.md. However, these are legitimate targets for the skill's stated purpose of managing AI agent instructions. The skill only writes template data to these files and backs up existing content to a local directory (~/.local/state/agent-skills/). No network exfiltration was found.
  • [SAFE]: All dependencies listed in uv.lock and pyproject.toml (e.g., typer, loguru, rich) are well-known, standard libraries from the official PyPI registry. The skill does not download external scripts or packages at runtime.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 26, 2026, 06:00 PM
Security Audit — agent-trust-hub — writing-style