The Agent Skills Directory

[SAFE]: The skill performs local filesystem read operations scoped to package.json files and workspace directories. No evidence of unauthorized file access, credential harvesting, or network-based data exfiltration was found.
[SAFE]: No remote code execution or untrusted dependency patterns were identified. The implementation relies on standard Node.js built-in modules (node:fs, node:path).
[SAFE]: The skill uses ANSI escape sequences in scripts/formatters/table.js exclusively for terminal UI coloring and formatting, which is standard practice for CLI tools and does not constitute malicious obfuscation.
[SAFE]: Instructions in SKILL.md are descriptive and technical, focusing on the tool's auditing purpose without attempting to override agent safety guidelines or system prompts.

browser-native