The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes local shell commands using git and the GitHub CLI (gh) to view repository metadata, pull request details, and code differences. These are standard operations for a development-focused agent environment.
[PROMPT_INJECTION]: The skill processes external data from pull request descriptions via gh pr view and code diffs via git diff. This represents an indirect prompt injection surface where adversarial content in code comments or PR metadata could attempt to influence the agent's logic.
Ingestion points: Data enters the context from gh pr view and git diff outputs as described in SKILL.md.
Boundary markers: No explicit markers or instructions to ignore embedded instructions are used when processing these inputs.
Capability inventory: Across its scripts and instructions, the agent can execute shell commands (git, gh) and invoke other skills (/ship, /split-and-ship, /polish-code).
Sanitization: No explicit sanitization, validation, or filtering of the ingested external content is defined.

finalize