The Agent Skills Directory

[SAFE]: The skill provides legitimate version control instructions and command-line examples for the Jujutsu tool.
[INDIRECT_PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection as it processes repository data and user-provided commit descriptions.
Ingestion points: Repository history, file contents via jj diff, and user input via jj desc are incorporated into the agent's context.
Boundary markers: No specific delimiters or safety warnings for handling untrusted data are provided in the instructions.
Capability inventory: The skill uses bash to execute version control commands like jj and git.
Sanitization: No explicit sanitization or validation of external content is defined.

jj-core