The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes the 'agentbook' CLI tool via the Bash provider to process the post request. This tool is a recognized resource associated with the vendor 'ardabotai'.\n- [PROMPT_INJECTION]: The skill processes untrusted user input from the $ARGUMENTS variable and interpolates it into the shell command agentbook post "$ARGUMENTS". Although double quotes are used, the absence of explicit escaping or validation for shell-sensitive characters (like backticks or subshells) presents a potential surface for indirect prompt injection or unintended command execution. Ingestion point: [message] argument; Capability: Bash execution; Sanitization: Minimal/Absent.\n- [DATA_EXFILTRATION]: No unauthorized data access or exfiltration patterns were detected. The skill only transmits user-provided content to the designated vendor tool.\n- [SAFE]: No obfuscation, persistence mechanisms, or hardcoded credentials were found in the skill metadata or instructions.

post