The Agent Skills Directory

[COMMAND_EXECUTION]: The skill provides various shell commands for network scanning and service interaction. This includes the use of Nmap scripts, Netcat for protocol commands, Metasploit modules, and PHP one-liners for data retrieval.- [PRIVILEGE_ESCALATION]: The skill instructs the user or agent to install system packages using administrative privileges. Evidence includes the use of sudo apt install libmemcached-tools and sudo apt-get install php-memcached for environment preparation.- [INDIRECT_PROMPT_INJECTION]: The skill facilitates the ingestion of untrusted data from remote Memcached servers, creating a vulnerability surface for indirect prompt injection.
Ingestion points: Data is retrieved via nc, memccat, and php commands in SKILL.md (Phase 3) and references/memcache-techniques.md.
Boundary markers: No delimiters or safety instructions are provided to distinguish retrieved cache content from agent instructions.
Capability inventory: The skill possesses extensive capabilities including shell command execution, network access, and package installation.
Sanitization: Content retrieved from the remote server is processed without sanitization or validation.

memcache-pentesting