The Agent Skills Directory

[SAFE]: No malicious instructions, obfuscation, or unauthorized data access patterns were identified across the skill files.
[COMMAND_EXECUTION]: The skill executes git and gh commands via the Bash tool to create branches and link issues. This functionality is consistent with the skill's documentation and is restricted by the allowed-tools configuration in the YAML frontmatter.
[INDIRECT_PROMPT_INJECTION]: The skill incorporates user input into branch names, creating a potential surface for indirect prompt injection.
Ingestion points: User-provided descriptions used to generate branch names in SKILL.md and rules/prefix-detection.md.
Boundary markers: Absent; user input is interpolated based on natural language instructions.
Capability inventory: File system operations and network requests via git and gh tools.
Sanitization: Present; rules/branch-naming.md provides explicit validation instructions for the model to lowercase text, replace characters, and reject specific symbols, mitigating standard command injection risks.

create-branch