The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local shell commands using the jj and gh tools to manage repository state, resolve conflicts, and interact with remote repositories.
[DATA_EXFILTRATION]: The skill performs network operations via jj git push and gh pr create to transmit code and metadata to GitHub. These operations are consistent with the skill's primary purpose and target a well-known service.
[PROMPT_INJECTION]: The skill ingests untrusted data from the repository history and file changes, which constitutes a surface for indirect prompt injection (Category 8). 1. Ingestion points: Untrusted data from the local repository enters the agent's context through commands such as jj status, jj diff, and jj log. 2. Boundary markers: The instructions do not define delimiters or specific markers to isolate repository-sourced text from agent instructions. 3. Capability inventory: The skill possesses capabilities to modify the local file system (jj describe, jj new) and perform network operations (jj git push, gh pr create). 4. Sanitization: No evidence of sanitization or validation of the ingested repository data is present in the skill's instructions.

jj