The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using git, gh (GitHub CLI), and wt (Worktrunk) to perform repository operations, including branch querying, committing, pushing, and merging.
[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface in its "pre-flight" step (Step 0), which instructs the agent to read and follow instructions from various repository files such as AGENTS.md, .clinerules, and .cursor/rules/*. A malicious repository could use these files to provide instructions that override the agent's behavior.
Ingestion points: The agent reads AGENTS.md, CLAUDE.md, CONTRIBUTING.md, .cursor/rules/*, .github/copilot-instructions.md, and .clinerules in SKILL.md.
Boundary markers: Absent. The skill directs the agent to "follow any @-includes" and verify the branch satisfies the rules without specific isolation or sanitization.
Capability inventory: The skill has capabilities to modify the local and remote repository state, including performing merges and pushing to the main branch remote.
Sanitization: Absent. Content from the rule files is treated as authoritative for the repository workflow.

done