The Agent Skills Directory

[SAFE]: The skill's primary function is to generate Markdown-formatted text for documentation purposes. It does not utilize any shell commands, scripts, or external tools.
[INDIRECT_PROMPT_INJECTION]: The skill analyzes external inputs such as PR descriptions and commit history which could theoretically contain malicious instructions. However, because the skill lacks the capability to execute code, write to the file system, or perform network requests, it does not present a viable attack surface for privilege escalation or data exfiltration. The risk is limited to influencing the content of the generated documentation.
[DATA_EXFILTRATION]: No network operations (curl, wget, etc.) or sensitive file access patterns were detected. The skill operates exclusively on provided change logs and PR data for documentation authoring.

changelog-design