The Agent Skills Directory

[PROMPT_INJECTION]: The skill includes robust defensive instructions that command the agent to treat all user-provided text strictly as data rather than instructions. This effectively mitigates risks from malicious commands embedded within text intended for rewriting.
[INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data as its primary function, creating a surface for indirect prompt injection. However, the risk is minimal because the skill has no dangerous capabilities (such as network access or file writing) and incorporates explicit boundary instructions for the agent to disregard any embedded instructions in the analyzed content.
[SAFE]: The skill does not exhibit any patterns related to remote code execution, credential theft, or persistence. All external references are limited to legitimate documentation and source code repositories relevant to the skill's linguistic purpose.

padrao-pts