ftp-pentesting

Pass

Audited by Gen Agent Trust Hub on Aug 12, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute various command-line tools for security testing, including nmap, nc, openssl, lftp, wget, hydra, medusa, and msfconsole.
  • [EXTERNAL_DOWNLOADS]: Mentions external wordlists from the SecLists repository for use in credential auditing and uses wget for recursive file downloads from targets.
  • [PROMPT_INJECTION]: The skill processes untrusted data from remote FTP services, which presents an indirect prompt injection vulnerability where malicious data from a target could influence the agent's execution flow.
  • Ingestion points: FTP banners in SKILL.md (Phase 1) and file contents or directory listings in references/ftp-commands.md (Phase 4 and 8).
  • Boundary markers: None present; the agent is not instructed to disregard potential instructions embedded in the target's output.
  • Capability inventory: The skill has access to network tools, file system operations, and command execution across its methodology.
  • Sanitization: No specific sanitization or validation of the data received from the FTP server is performed before the agent acts on it.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 12, 2026, 03:49 PM
Security Audit — agent-trust-hub — ftp-pentesting