ad-ldap-attack

Fail

Audited by Gen Agent Trust Hub on Sep 19, 2026

Risk Level: CRITICALEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill's documentation references an external domain that is blacklisted by security reputation services. Evidence: The URL https://rastamouse.me/ is cited in guides/ad-lateral-movement-guide.md as a resource. Automated scans by URLite have flagged this specific domain as malicious. Referring users or agents to blacklisted external sites is a security risk.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection attacks because it processes untrusted data from network services. Ingestion points: Data is retrieved from Active Directory objects and NetBIOS services via tools like ldapsearch, bloodhound-python, and nbtscan. Boundary markers: The skill does not provide delimiters or instructions to ignore embedded commands within the ingested data. Capability inventory: The skill utilizes Bash, Write, Edit, and WebFetch tools. Sanitization: No sanitization or validation logic is present to ensure that data fetched from potentially compromised or adversary-controlled Active Directory attributes (e.g., sAMAccountName, description) does not contain malicious instructions for the agent.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool extensively to execute complex security testing commands and system interactions. Evidence: Multiple shell commands in SKILL.md and payloads.md provide templates for significant system and network manipulation.
Recommendations
  • Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata
Risk Level
CRITICAL
Analyzed
Sep 19, 2026, 04:36 PM