egyptian-web-audit
Pass
Audited by Gen Agent Trust Hub on Sep 26, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill consists entirely of markdown instructions and checklists for performing a manual or AI-assisted audit. No scripts, binaries, or automated network commands are included. No malicious scripts, hardcoded credentials, obfuscation, or persistence mechanisms were detected.
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to analyze external, untrusted content (websites and apps), creating a surface for indirect prompt injection.
- Ingestion points: External websites and product flows being audited (SKILL.md).
- Boundary markers: None provided in the instructions to delimit external content.
- Capability inventory: Capturing screenshots, inspecting DOM/CSS details, and simulating user interactions (SKILL.md).
- Sanitization: No specific sanitization or filtering of external content is defined in the workflow.
Audit Metadata