n8n:create-pr
Pass
Audited by Gen Agent Trust Hub on Aug 19, 2026
Risk Level: SAFE
Full Analysis
- [COMMAND_EXECUTION]: Uses standard
gitandgh(GitHub CLI) commands to check repository status, push branches, and create pull requests. These operations are within the scope of the declaredallowed-tools. - [DATA_EXPOSURE]: Explicitly instructs the agent to avoid disclosing security vulnerability details in public artifacts like branch names, PR titles, or commit messages, which is a defensive security practice.
- [INDIRECT_PROMPT_INJECTION]: The skill interpolates content from the repository (branch names, plan files, and PR templates) into the pull request body.
- Ingestion points: Reads files from
.claude/plans/,.agents/plans/, and.github/pull_request_template.md, as well as branch names and git logs. - Boundary markers: Employs quoted heredocs (
'EOF') in the command examples to prevent shell expansion of the generated body content. - Capability inventory: Can perform
git pushandgh pr create(write operations). - Sanitization: Relies on the AI to process and format templates based on gathered context.
Audit Metadata