Red Team Tools and Methodology
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTIONEXTERNAL_DOWNLOADS
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from external web sources, creating an attack surface for indirect prompt injection.
- Ingestion points: The skill retrieves subdomains, URL paths, technology fingerprints, and parameter lists from target domains using tools such as
subfinder,amass,httpx, andwaybackurls(SKILL.md, Sections 2, 3, 5). - Boundary markers: The instructions do not specify any delimiters or safety warnings to ignore malicious instructions embedded within the retrieved data.
- Capability inventory: The skill utilizes extensive capabilities, including network vulnerability scanning (
nuclei,ffuf), parameter manipulation (qsreplace), and file system operations (mkdir,tee) (SKILL.md, Sections 5, 8, 10). - Sanitization: There is no evidence of sanitization, escaping, or validation of retrieved external data before it is used as input for subsequent tool chains.
- [COMMAND_EXECUTION]: The skill contains a large variety of shell commands and a dedicated bash script for automating security reconnaissance and vulnerability discovery (SKILL.md, Section 10).
- [EXTERNAL_DOWNLOADS]: Retrieves reconnaissance data and ASN information from the well-known service bgp.he.net (SKILL.md, Section 1).
Audit Metadata