The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructions frequently use the sudo command to execute ksubdomain (e.g., sudo ksubdomain enum ...). Requiring root privileges for network operations is a high-risk pattern as it provides the tool with full system access, increasing the impact of any potential vulnerabilities.
[EXTERNAL_DOWNLOADS]: The skill references and relies on an external tool, ksubdomain, hosted on a third-party GitHub repository (github.com/boy-hack/ksubdomain). This creates a dependency on unverified third-party software, which is a potential supply chain risk.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes data from untrusted external files and passes them as arguments to shell commands without sanitization.
Ingestion points: Reads subdomains, wordlists, and resolvers from files (e.g., subdomains.txt, wordlist.txt).
Boundary markers: None used to separate untrusted file content from the command logic.
Capability inventory: Commands are executed with root privileges (sudo) and can write results to the file system (-o).
Sanitization: There is no evidence of input validation or escaping for the contents of the files being processed.

ksubdomain-brute