Audit History

All 17 static findings are false positives caused by Markdown code fences, inline code, and fixed relative documentation links. The skill documents an intended gws Gmail send command and requires user confirmation before its external write action. No prompt injection or hidden exfiltration intent was found.

The static external command and path traversal alerts are false positives caused by Markdown code fences, inline code, and relative documentation links. The skill has a real business-logic risk because it sends Gmail messages and can attach local files, but it includes a caution to confirm before execution.

The static external command and path traversal alerts are false positives caused by Markdown code fences, inline code, and relative documentation links. The skill has a real business-logic risk because it sends Gmail messages and can attach local files, but it includes a caution to confirm before execution.

Static findings for shell backticks, path traversal, and weak cryptography are false positives in Markdown documentation and table syntax. The skill still has medium operational risk because it instructs an agent to run a Gmail write command that can send messages and attach local files, so user confirmation is required.

All 20 static analysis findings are false positives from Markdown code examples. The external_commands flags (15 occurrences) are bash documentation blocks showing gws CLI usage. The filesystem flags (3 occurrences) are relative path references in documentation links. This is legitimate documentation for a Gmail CLI tool with no executable code or security risks.