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 inguides/ad-lateral-movement-guide.mdas 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, andnbtscan. Boundary markers: The skill does not provide delimiters or instructions to ignore embedded commands within the ingested data. Capability inventory: The skill utilizesBash,Write,Edit, andWebFetchtools. 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
Bashtool extensively to execute complex security testing commands and system interactions. Evidence: Multiple shell commands inSKILL.mdandpayloads.mdprovide templates for significant system and network manipulation.
Recommendations
- Contains 1 malicious URL(s) - DO NOT USE
Audit Metadata