The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted data from git diff, git log, and external issue tickets to populate pull request titles and bodies. This creates a potential surface for indirect prompt injection where instructions embedded in code changes or tickets could influence the agent. Ingestion points: Git history commands and ticket content referenced in SKILL.md. Boundary markers: None explicitly defined. Capability inventory: Pull request creation and editing via gh and glab CLI tools. Sanitization: The process includes a mandatory 'secrets check' and a 'humanizer pass' as part of the cleanup steps in SKILL.md.
[COMMAND_EXECUTION]: The skill executes shell commands using standard tools including git for status and diffs, gh (GitHub CLI), and glab (GitLab CLI) for pull request management. These commands are typical for developer workflows and are correctly scoped to the skill's purpose.

create-pr