smb-enumeration

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill processes untrusted data from remote SMB shares via manspider and smbclient, which creates a surface for indirect prompt injection.
  • Ingestion points: Data retrieved from SMB shares during file listings and content searches (SKILL.md Steps 4 and 6).
  • Boundary markers: The instructions do not define delimiters or specific safety instructions for the agent when interpreting results from the target host.
  • Capability inventory: The skill uses network-capable tools (smbclient, NetExec, enum4linux-ng, nmap) and performs file system writes (smbclient put).
  • Sanitization: No explicit sanitization or filtering is performed on data retrieved from the target before processing.
  • [COMMAND_EXECUTION]: The skill executes multiple security tools via the command line, including smbclient, NetExec, enum4linux-ng, manspider, and nmap.
  • Evidence: Commands in Steps 1, 2, 3, 4, 5, 6, and 7.
  • Context: These operations are core to the skill's stated purpose of SMB enumeration in a penetration testing context.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 09:16 AM
Security Audit — agent-trust-hub — smb-enumeration