metasploit
Pass
Audited by Gen Agent Trust Hub on Oct 11, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_CONTEXT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes shell commands for Metasploit tools (msfconsole, msfvenom) and local wrapper scripts. These commands take arguments like LHOST, LPORT, and target targets, which flow into the shell execution environment.
- [INDIRECT_PROMPT_INJECTION]: The skill processes output from network service scans and auxiliary modules. This creates a surface where malicious instructions embedded in target service banners or responses could influence agent behavior if processed without adequate sanitization.
- Ingestion points: Service scanning results from msfconsole auxiliary modules and local wrapper scripts referenced in SKILL.md.
- Boundary markers: No specific delimiters or warnings for the agent to ignore instructions embedded in the tool output are provided in the skill instructions.
- Capability inventory: Shell command execution via bash, msfconsole, and msfvenom across all modules.
- Sanitization: The skill lacks explicit logic to sanitize, escape, or filter external content returned by the scanning tools before it is interpreted by the agent.
- [DYNAMIC_CONTEXT_INJECTION]: The skill uses the dynamic injection syntax (!command) in SKILL.md to check for the presence of the msfconsole binary and local wrapper scripts at load time. These commands are used for environmental status checks and do not perform sensitive data access or exfiltration.
Audit Metadata