active-directory-technique
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides numerous commands for executing offensive security tools like Impacket, BloodHound, and Certipy to perform domain enumeration, lateral movement, and privilege escalation.- [DATA_EXFILTRATION]: Provides instructions for harvesting sensitive information, including dumping LSASS memory for credentials and extracting the NTDS.dit database from Domain Controllers. These actions are standard for the skill's intended purpose.- [EXTERNAL_DOWNLOADS]: Fetches tools such as PsExec from Microsoft's official Sysinternals domain to facilitate authorized security testing workflows.- [INDIRECT_PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection as it processes output from external CLI tools (e.g., BloodHound query results, LDAP enumeration) without explicit sanitization.
- Ingestion points: CLI output from tools like
bloodhound-pythonandenum4linux-ngprocessed by the agent (SKILL.md). - Boundary markers: No explicit delimiters or warnings to ignore instructions embedded in tool output are present.
- Capability inventory: The skill enables subprocess execution of numerous tools, file writes to the local system, and network operations across all phases.
- Sanitization: No evidence of sanitization or validation of data ingested from external tool outputs.
Audit Metadata