The Agent Skills Directory

[SAFE]: The skill consists entirely of instructional Markdown files intended to guide the AI assistant. It does not contain any scripts, binaries, or automated installation hooks that could execute arbitrary code.
[SAFE]: The instructions focus on the use of the but CLI tool for version control tasks. All documented commands are standard development operations like committing, branching, and resolving conflicts, consistent with the skill's stated purpose.
[INDIRECT_PROMPT_INJECTION]: The skill interacts with external data sources (Git repositories) which constitutes an inherent surface for indirect prompt injection.
Ingestion points: The skill ingests untrusted data from the repository through commands such as but diff, but status, but show, and but branch list as described in SKILL.md and references/reference.md.
Boundary markers: The instructions do not specify the use of delimiters or specific boundary markers for data retrieved from the CLI output.
Capability inventory: The skill grants the agent the ability to execute but CLI commands and modify files within the user's workspace.
Sanitization: There are no instructions for sanitizing or filtering the content retrieved from the version control system before processing.
[SAFE]: No obfuscation, malicious prompt injection patterns, or persistence mechanisms were detected. All external links point to official documentation or generic repository placeholders.

but