red-team-tools

Pass

Audited by Gen Agent Trust Hub on Apr 1, 2026

Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill provides numerous bash commands and a shell script (recon.sh) that automate the use of various security tools.
  • Evidence: Includes instructions for executing amass, subfinder, nuclei, ffuf, httpx, waybackurls, and dalfox.
  • Context: These tools are standard for the skill's stated purpose of red-teaming and vulnerability discovery.
  • [DATA_EXFILTRATION]: The skill performs reconnaissance by querying external services.
  • Evidence: Fetches information from bgp.he.net and mentions prerequisites for API keys for services like Shodan and Censys.
  • Context: These are well-known technology and security services used for legitimate research; no unauthorized exfiltration of sensitive user data is present.
  • [PROMPT_INJECTION]: The skill processes data from external web sources which could potentially contain malicious instructions (Indirect Prompt Injection surface).
  • Ingestion points: The skill ingests data from external targets through tool outputs from httpx, waybackurls, and nuclei.
  • Boundary markers: No boundary markers are used in the scripts to isolate external content from the agent's instructions.
  • Capability inventory: The skill has the capability to execute shell commands and write files to the local system.
  • Sanitization: No sanitization or filtering of external content is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 1, 2026, 03:59 AM