The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill requires the agent to process user-supplied values, such as domain names and file paths, and interpolate them into shell commands and configuration files. This creates a surface for potential command injection or path traversal if the user provides malicious input. * Ingestion points: User-provided FQDNs and directory paths processed across all five phases in SKILL.md. * Boundary markers: The instructions do not specify the use of delimiters or data-ignoring prompts for the agent when handling these inputs. * Capability inventory: The skill utilizes Bash, Write, and Edit tools to perform system modifications via shell commands. * Sanitization: No validation or sanitization steps are defined for external inputs before they are passed to shell tools.
[COMMAND_EXECUTION]: The skill directs the agent to execute various system-level commands, including ufw, systemctl, apt-get, and certbot. The use of ufw --force enable explicitly bypasses interactive prompts. While these actions are central to the skill's purpose, they involve high-privilege capabilities that could be abused if the agent is misled by malicious user input.

public-web-deploy