Audit History

Most static findings are false positives from Markdown examples, placeholder API keys, expected output writes, and documented optional provider URLs. Two sudo package installation instructions are confirmed because they require elevated privileges. A semantic issue notes that the skill steers users toward external generation and hosted-platform workflows beyond document conversion.

Most static findings are false positives from Markdown examples, placeholder API keys, expected output writes, and documented optional provider URLs. Two sudo package installation instructions are confirmed because they require elevated privileges. A semantic issue notes that the skill steers users toward external generation and hosted-platform workflows beyond document conversion.

Most static hits are documentation examples or scanner noise around Markdown code fences, placeholder API keys, expected file writes, and error messages. Confirmed risks are optional third-party network processing, environment use of OPENROUTER_API_KEY, and sudo installation instructions for Tesseract. Semantic review also found third-party document disclosure risk and unrelated promotional steering.

Most static hits are documentation examples or scanner noise around Markdown code fences, placeholder API keys, expected file writes, and error messages. Confirmed risks are optional third-party network processing, environment use of OPENROUTER_API_KEY, and sudo installation instructions for Tesseract. Semantic review also found third-party document disclosure risk and unrelated promotional steering.

Static analysis produced a critical score because Markdown examples contain shell commands, URLs, API key placeholders, and local file writes. Review found no confirmed malicious intent or hidden exfiltration, but the skill has broad tool permissions, optional outbound AI calls, plugin support, and promotional behavior instructions. Publish with warnings for network use, local writes, plugin trust, and review of generated commands before execution.

Static findings are false positives. The scanner incorrectly flagged markdown code blocks (using backticks) as shell execution, and legitimate document conversion patterns as suspicious. The skill is a Microsoft tool for converting documents to Markdown with expected file I/O and API access.

Static findings are false positives. The scanner incorrectly flagged markdown code blocks (using backticks) as shell execution, and legitimate document conversion patterns as suspicious. The skill is a Microsoft tool for converting documents to Markdown with expected file I/O and API access.

All 366 static findings are false positives. The analyzer incorrectly flagged documentation code examples as executed commands. This is a benign file conversion tool that wraps Microsoft's MarkItDown library for converting documents to Markdown format.

This is a file conversion wrapper skill for Microsoft's MarkItDown. Filesystem access is limited to user-specified paths for conversion. Network usage is restricted to OpenRouter API calls for optional AI image descriptions. No credential theft, exfiltration, or dangerous execution patterns detected.