subdomain-enum

Pass

Audited by Gen Agent Trust Hub on Aug 19, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches specialized security tools from the official ProjectDiscovery and OWASP-Amass GitHub repositories via the go install command.
  • [COMMAND_EXECUTION]: Executes several CLI tools including subfinder, amass, and httpx to perform reconnaissance, along with standard shell utilities for file management and data processing.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from the internet. 1. Ingestion points: httpx collects web page titles and technology metadata from external servers; subfinder and amass collect subdomain strings from various public sources. 2. Boundary markers: Not present. The skill does not employ delimiters to separate external data from the agent's internal instructions. 3. Capability inventory: The skill possesses the ability to execute shell commands and write to the local file system. 4. Sanitization: None. Data collected from external sources is processed and displayed without filtering or escaping.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 19, 2026, 06:16 AM
Security Audit — agent-trust-hub — subdomain-enum