tools-metasploit
Pass
Audited by Gen Agent Trust Hub on Oct 15, 2026
Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: Provides specific shell command patterns for invoking Metasploit components (msfconsole, msfrpcd) with complex arguments for non-interactive automation, including process cleanup commands like pkill.
- [EXTERNAL_DOWNLOADS]: Includes instructions to fetch the agent's public IP address from the well-known service api.ipify.org for reverse shell configuration.
- [INDIRECT_PROMPT_INJECTION]:
- Ingestion points: The skill instructions involve processing vulnerability data and mapping it to specific Metasploit modules.
- Boundary markers: Absent; instructions do not specify delimiters for untrusted input data.
- Capability inventory: Full Metasploit capability set, including exploit execution, reverse shell handlers, and session interaction.
- Sanitization: Absent; the skill assumes the agent selects modules and parameters based on its internal logic without explicit validation steps defined in the script patterns.
Audit Metadata