attacking-kerberos-delegation
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes several offensive security tools including Impacket scripts, Rubeus, and Mimikatz. These are standard tools used in authorized penetration testing.
- [PROMPT_INJECTION]: The skill instructions define command-line templates that interpolate untrusted user data, creating a surface for indirect prompt injection. 1. Ingestion points: Arguments for credentials, domain names, and target addresses in the bash code blocks within SKILL.md. 2. Boundary markers: Absent; the agent is not instructed to validate or sanitize these inputs. 3. Capability inventory: Use of tools capable of credential extraction and network-based impersonation. 4. Sanitization: No input validation or sanitization logic is provided for the user-controlled variables.
Audit Metadata