wordpress-penetration-testing

Warn

Audited by Gen Agent Trust Hub on Feb 27, 2026

Risk Level: MEDIUMCOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructions require the execution of various command-line tools such as wpscan, nmap, and curl to perform security scanning and data retrieval.
  • [REMOTE_CODE_EXECUTION]: The skill provides functional code for creating webshells and reverse shells, facilitating the deployment of malicious code to remote targets.
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection. 1. Ingestion points: Data is fetched from untrusted remote URLs via curl and wpscan in multiple phases. 2. Boundary markers: No delimiters or ignore instructions are used to separate fetched content from the agent's instructions. 3. Capability inventory: The agent has access to shell execution (bash), local file creation (cat), and exploitation frameworks (msfconsole). 4. Sanitization: There is no validation or sanitization performed on the content retrieved from external targets before it is processed by the agent.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 27, 2026, 11:21 PM