network-password-spraying

Pass

Audited by Gen Agent Trust Hub on Sep 20, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill describes processes for ingesting external data and executing command-line tools based on that data, creating a vulnerability surface where malicious input in external files could influence agent behavior.
  • Ingestion points: The skill references external files such as users.txt for credentials, and roe.md or scope.txt for rules of engagement (referenced in SKILL.md).
  • Boundary markers: The skill instructs the agent to confirm authorization in scope files but lacks explicit prompt boundary markers or "ignore embedded instructions" warnings for processing the user-provided data.
  • Capability inventory: The skill utilizes multiple network authentication tools including nxc (NetExec), kerbrute, hydra, and msspray to perform active network operations.
  • Sanitization: There is no mention of sanitization, validation, or escaping of the content found within the external users.txt or scope files before they are utilized in commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 20, 2026, 11:02 PM
Security Audit — agent-trust-hub — network-password-spraying