Histórico de auditoria
building-agent-tools - 6 auditorias
Versão da auditoria 6
Mais recente Baixo RiscoJun 28, 2026, 06:02 PM
Static analysis reported external command, weak cryptography, and reconnaissance patterns, but review found only Markdown prose and inline identifiers. No executable code, prompt injection attempt, network access, filesystem access, or credential handling was found in SKILL.md.
Problemas de Baixo Risco (3)
Versão da auditoria 5
SeguroJan 16, 2026, 07:21 PM
Pure documentation skill containing only markdown guidance for designing AI agent tools. No executable code, no file system access, no network calls, no command execution. All 50 static findings are false positives triggered by pattern matching on documentation text without semantic understanding.
Fatores de risco
⚙️ Comandos externos (7)
Versão da auditoria 4
SeguroJan 16, 2026, 07:21 PM
Pure documentation skill containing only markdown guidance for designing AI agent tools. No executable code, no file system access, no network calls, no command execution. All 50 static findings are false positives triggered by pattern matching on documentation text without semantic understanding.
Fatores de risco
⚙️ Comandos externos (7)
Versão da auditoria 3
SeguroJan 10, 2026, 11:42 AM
Pure documentation skill containing only markdown guidance for designing AI agent tools. No executable code, no file system access, no network calls, no command execution. This is instructional content only.
Versão da auditoria 2
SeguroJan 10, 2026, 11:42 AM
Pure documentation skill containing only markdown guidance for designing AI agent tools. No executable code, no file system access, no network calls, no command execution. This is instructional content only.
Versão da auditoria 1
SeguroJan 10, 2026, 11:42 AM
Pure documentation skill containing only markdown guidance for designing AI agent tools. No executable code, no file system access, no network calls, no command execution. This is instructional content only.