The Agent Skills Directory

[SAFE]: The skill package is composed entirely of Markdown documentation and templates. There are no executable files, scripts, or configurations that trigger code execution.
[SAFE]: Both SKILL.md and references/INTAKE.md contain explicit prohibitions against requesting sensitive user information, such as credentials or private data.
[PROMPT_INJECTION]: No patterns of malicious instruction overrides, jailbreaks, or safety filter bypasses were detected in the instructions or metadata.
[DATA_EXFILTRATION]: The skill does not utilize any tools or commands capable of network transmission or data exfiltration.
[COMMAND_EXECUTION]: There is no evidence of shell command usage, script generation, or runtime execution patterns across any of the analyzed files.

content-marketing