The Agent Skills Directory

[Prompt Injection] (SAFE): The skill instructions are benign and follow standard instructional patterns without attempting to bypass safety filters or override system prompts.
[Data Exposure & Exfiltration] (SAFE): No hardcoded credentials, sensitive file paths, or network operations were found.
[Remote Code Execution] (SAFE): There are no external scripts, package installations, or dynamic code execution patterns present.
[Indirect Prompt Injection] (LOW): This skill has a minimal attack surface.
Ingestion points: The skill accepts user input via the [optional parameters] in the /example command.
Boundary markers: Absent; the input is interpreted directly by the agent.
Capability inventory: None; the skill only generates text responses and has no access to shell, file system, or network tools.
Sanitization: Absent, but not required given the lack of dangerous capabilities.

example