subdomain-deep

Pass

Audited by Gen Agent Trust Hub on Apr 22, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill includes shell scripts and command-line tool usage for DNS enumeration and wildcard filtering in references/enumeration-tools.md. These scripts use tools like dig, curl, and md5sum to process domain lists.
  • [EXTERNAL_DOWNLOADS]: The skill references and provides usage instructions for several external security tools including subfinder, ksubdomain, amass, katana, and httpx.
  • [DATA_EXFILTRATION]: The skill methodology involves outbound network requests to OSINT engines and target websites to collect asset information, which involves sending domain-related data to these external services.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection. Ingestion points: SKILL.md (Phase 3) describes crawling and extracting data from external websites (HTML, JS, CSS). Boundary markers: The instructions lack delimiters or explicit markers to prevent the agent from obeying instructions embedded in the crawled content. Capability inventory: The skill uses a wide range of powerful CLI tools for network scanning and system interaction. Sanitization: There is no evidence of sanitization, filtering, or validation of the content retrieved from external sources before it is processed by the agent.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 22, 2026, 10:08 AM