remote-access-enumeration

Pass

Audited by Gen Agent Trust Hub on Jul 6, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses nmap, ftp, ssh, and evil-winrm to interact with remote targets. These are standard tools for security auditing and their usage is consistent with the skill's stated purpose of penetration testing enumeration.
  • [INDIRECT_PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection as it ingests and processes untrusted data from external targets.
  • Ingestion points: Target file listings, service banners, and the contents of configuration files (e.g., .htpasswd, web.config) are read into the agent's context in Step 1 (FTP) and Step 2 (SSH).
  • Boundary markers: Absent; the instructions do not specify using delimiters or instructions to ignore embedded content when reading from targets.
  • Capability inventory: The agent can execute shell commands (nmap, ftp, ssh, evil-winrm), write to the local file system (./engagement/evidence/), and update its internal state via functions like add_vuln and add_credential.
  • Sanitization: The skill does not describe any validation or escaping of the data retrieved from remote hosts before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 6, 2026, 09:15 AM
Security Audit — agent-trust-hub — remote-access-enumeration