The Agent Skills Directory

[COMMAND_EXECUTION]: The skill requires administrative privilege escalation by using sudo tee -a /etc/hosts to modify the system's local DNS resolution file. This allows the agent to perform actions with root-level access.
[PROMPT_INJECTION]: There is a vulnerability to indirect prompt injection as the skill ingests data from external tool outputs (ffuf, openssl, and dnsx) into the agent's context without any boundary markers or sanitization.
Ingestion points: The skill reads data from vhost_ffuf.json, ssl_hostnames.txt, ptr_domains.txt, and found_vhosts.txt.
Boundary markers: No explicit delimiters or instructions to ignore embedded malicious content are present.
Capability inventory: The agent has access to terminal command execution, network requests via curl/openssl, and the ability to modify system files.
Sanitization: No validation or filtering is applied to the data retrieved from the network tools before processing.
[COMMAND_EXECUTION]: The skill constructs shell commands using variables like TARGET_IP and host without proper input validation, which could lead to command injection if the input source is compromised or contains shell metacharacters.

vhost-enumeration