gobuster

Pass

Audited by Gen Agent Trust Hub on Sep 3, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill facilitates the execution of the gobuster CLI tool by providing shell command templates in SKILL.md. This allows the agent to perform network-based enumeration tasks using the shell.\n- [INDIRECT_PROMPT_INJECTION]: The skill defines an attack surface where untrusted external data such as target URLs or wordlists is used to construct shell commands. \n
  • Ingestion points: The Inputs section allows for the entry of URLs, hosts, domains, and wordlists (SKILL.md). \n
  • Boundary markers: Absent. There are no instructions for the agent to use delimiters or sanitization routines for the input data. \n
  • Capability inventory: The skill uses subprocess calls to execute gobuster subcommands like dir, dns, and vhost. \n
  • Sanitization: Absent. The skill does not provide mechanisms for filtering or escaping special characters in the provided arguments before they are executed in the shell.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 3, 2026, 02:38 AM
Security Audit — agent-trust-hub — gobuster