The Agent Skills Directory

[SAFE]: The skill is a set of instructions designed to improve the clarity of the agent's communication. It does not contain any malicious patterns such as command execution, data exfiltration, or obfuscation. It uses standard platform configuration to define its behavior.
[INDIRECT_PROMPT_INJECTION]: The skill identifies an attack surface by instructing the agent to process and re-pitch its own previous output. However, because the skill has no high-privilege capabilities such as shell execution, file system modification, or network access, this surface does not present a security risk.

meaning