WordPress Penetration Testing
Warn
Audited by Gen Agent Trust Hub on Mar 16, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill documentation provides instructions for running numerous security tools, including
nmapfor port scanning,wpscanfor WordPress vulnerability enumeration, and the Metasploit Framework (msfconsole) for exploitation tasks. - [REMOTE_CODE_EXECUTION]: The skill includes functional PHP and bash code snippets designed to create backdoors and reverse shells on target systems, specifically a PHP-based web shell using
system()and a bash command for interactive reverse shell access. - [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection as it ingests untrusted data from external websites and processes it using high-capability tools without explicit boundary markers or sanitization.
- Ingestion points: Content retrieved from target WordPress installations via
curl,wget, andwpscan(SKILL.md). - Boundary markers: Absent; there are no instructions to distinguish between retrieved target data and the agent's internal operational commands.
- Capability inventory: Includes powerful system utilities and shells such as
bash,msfconsole, and the ability to compile and execute PHP scripts (SKILL.md). - Sanitization: None; the skill lacks validation mechanisms for the content returned from scanned targets before it is passed to other tools or displayed to the user.
Audit Metadata