The Agent Skills Directory

[COMMAND_EXECUTION]: The skill methodology involves executing standard security tools such as nmap, hydra, medusa, ncrack, and msfconsole for auditing IMAP services. These tools are used within their intended scope for security testing.
[EXTERNAL_DOWNLOADS]: Includes instructions for the agent to install the 'evolution' mail client through the system package manager to assist in visualizing email data.
[PROMPT_INJECTION]: The skill creates a surface for indirect prompt injection as it is designed to retrieve and process content from external mail servers:
Ingestion points: Untrusted content enters the context via curl and imaplib fetches of email bodies and headers in SKILL.md and references/imap-techniques.md.
Boundary markers: Absent. The instructions do not define delimiters to separate fetched email data from agent instructions.
Capability inventory: The skill context includes access to powerful CLI tools (nc, openssl, nmap, hydra, curl) and package installation capabilities as described in SKILL.md.
Sanitization: Absent. There is no logic provided to sanitize or validate the content of the emails before they are analyzed by the agent.

imap-pentesting