Habilidades ai-image-generation Histórico de auditoria
📦

Histórico de auditoria

ai-image-generation - 1 auditoria

7 de out. de 2026, 15:00

All 199 static matches are false positives involving Markdown, public links, placeholder URLs, or documented token storage. One semantic finding identifies overbroad shell-safety guidance requiring explicit escaping before CLI execution. No evidence found of malicious instructions or credential exfiltration in the supplied file; the external CLI implementation was not reviewed.

1
Arquivos analisados
497
Linhas analisadas
4
Itens de revisão
0
Falsos positivos ignorados

Preocupações de segurança confirmadas (1)

Médio
Overbroad Shell-Safety Guidance
The claim "No shell-injection surface from prompt content" overlooks shell parsing before CLI execution. Unescaped prompt quotes can break shell arguments despite valid JSON.
The document makes an unconditional safety claim while using shell-quoted JSON. One example escapes an apostrophe correctly, but safety still depends on consistent shell escaping.

Fatores de risco

⚙️ Comandos externos (50)
🌐 Acesso à rede (50)
📁 Acesso ao sistema de arquivos (5)
Auditado por: codex