ad-attacks

Pass

Audited by Gen Agent Trust Hub on May 18, 2026

Risk Level: SAFE
Full Analysis
  • [SAFE]: Extensive analysis of the skill confirms it is purely instructional and documentation-based. It describes methodology for analyzing Active Directory security (such as BloodHound path analysis, Kerberos abuse, and ADCS flaws) for legitimate security assessments and defensive hardening purposes.
  • [EXTERNAL_DOWNLOADS]: The skill references several external resources, including official Microsoft repositories (e.g., New-KrbtgtKeys.ps1) and well-known security research sites (e.g., SpecterOps/GhostPack). These references are documented neutrally as authoritative sources for security protocols and auditing tools.
  • [COMMAND_EXECUTION]: No executable scripts or shell commands are included in the skill. It provides high-level descriptions of techniques and naming conventions (e.g., BloodHound edges, ATT&CK IDs) rather than automated attack scripts.
  • [PROMPT_INJECTION]: The skill does not contain any instructions aimed at bypassing AI safety filters or overriding system prompts. It maintains a professional tone and explicitly includes a 'Rules of Engagement (RoE)' policy to guide the user toward authorized use cases.
Audit Metadata
Risk Level
SAFE
Analyzed
May 18, 2026, 04:30 PM
Security Audit — agent-trust-hub — ad-attacks