The Agent Skills Directory

[SAFE]: The skill primary behavior involves analyzing local HTML files for web standards and quality metrics. All operations are local and read-only.\n- [SAFE]: No network operations, external downloads, or remote code execution patterns were detected. The skill relies on standard pre-installed utilities like grep and jq.\n- [SAFE]: The skill does not access sensitive files (e.g., credentials, SSH keys, environment files) or private user data. Its scope is limited to the directory or file path provided for auditing.\n- [SAFE]: No obfuscation, prompt injection, or persistence mechanisms (like crontabs or shell profile modifications) were found in the skill's instructions or scripts.\n- [SAFE]: The script uses jq to properly escape and format findings, which prevents data from the audited files from being misinterpreted as commands or malicious instructions. While it ingests external HTML content, the limited capability set (read-only grep) makes the risk of indirect prompt injection negligible.

web-quality-audit