subdomain-enumeration
Pass
Audited by Gen Agent Trust Hub on Jul 31, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied domain information which is interpolated directly into shell commands without sanitization. \n
- Ingestion points: The
DOMAINvariable and command line argument$1are used in shell templates across theSKILL.mdfile (e.g., in Step 1, Step 5, and Phase 8). \n - Boundary markers: Absent. The instructions do not define delimiters or provide warnings to the agent to treat the input as untrusted data. \n
- Capability inventory: The skill utilizes extensive shell execution capabilities including
curl,subfinder,httpx,dnsx,dig, andpuredns. \n - Sanitization: Absent. The
DOMAINand$1variables are used directly in shell commands without validation or escaping, which could allow for command injection if the input contains shell metacharacters. \n- [DATA_EXPOSURE_AND_EXFILTRATION]: Queries the well-known certificate transparency log service crt.sh and mentions the use of API keys in local configuration files (~/.config/subfinder/provider-config.yaml) for passive reconnaissance, which are standard and safe practices. \n- [EXTERNAL_DOWNLOADS]: Fetches an official list of Top Level Domains from IANA (data.iana.org), which is a trusted organization.
Audit Metadata