Audit History
add-backend-tool - 5 audits
Audit version 5
Latest SafeJan 16, 2026, 03:24 PM
Pure documentation skill containing only instructions and guidance. No executable code, no file operations, no network calls, no command execution. All 23 static findings are false positives from pattern-matching on documentation code examples. The scanner misidentified YAML front matter, JSON metadata fields, markdown code blocks, and security documentation as security vulnerabilities.
Risk Factors
🌐 Network access (1)
📁 Filesystem access (1)
⚙️ External commands (8)
Audit version 4
SafeJan 16, 2026, 03:24 PM
Pure documentation skill containing only instructions and guidance. No executable code, no file operations, no network calls, no command execution. All 23 static findings are false positives from pattern-matching on documentation code examples. The scanner misidentified YAML front matter, JSON metadata fields, markdown code blocks, and security documentation as security vulnerabilities.
Risk Factors
🌐 Network access (1)
📁 Filesystem access (1)
⚙️ External commands (8)
Audit version 3
SafeJan 10, 2026, 10:18 AM
Pure prompt-based skill containing only documentation and instructions. No executable code, no file access beyond its own SKILL.md, no network calls, no command execution. Contains only guidance for adding backend tools to an OpenAI function calling system.
Audit version 2
SafeJan 10, 2026, 10:18 AM
Pure prompt-based skill containing only documentation and instructions. No executable code, no file access beyond its own SKILL.md, no network calls, no command execution. Contains only guidance for adding backend tools to an OpenAI function calling system.
Audit version 1
SafeJan 10, 2026, 10:18 AM
Pure prompt-based skill containing only documentation and instructions. No executable code, no file access beyond its own SKILL.md, no network calls, no command execution. Contains only guidance for adding backend tools to an OpenAI function calling system.