The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes several shell commands using the GitHub CLI (gh) and git to manage the repository state. This includes querying branch information (gh repo view), creating and merging pull requests (gh pr create, gh pr merge), and updating repository settings (gh api -X PATCH). These operations are consistent with the skill's primary purpose of automating the PR workflow.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection (Category 8) as it ingests and processes data from potentially untrusted sources without explicit sanitization.
Ingestion points: The skill reads integration branch overrides from a CLAUDE.md file within the repository and processes arbitrary code diffs when invoking the /code-review skill.
Boundary markers: The instructions do not define delimiters or specific markers to prevent the agent from interpreting instructions that might be embedded within the CLAUDE.md file or the code diffs.
Capability inventory: The skill has broad capabilities including file system modification (git commit), branch deletion (git branch -d), and repository configuration changes via the GitHub API (gh api).
Sanitization: No validation or escaping is applied to the data retrieved from external sources before it is used to influence the agent's logic or included in generated PR summaries.

flow-pr