create-pull-request
Pass
Audited by Gen Agent Trust Hub on Sep 17, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute standard development commands including
git push,gh pr create,npm test, andnpm run lint. These are routine operations for managing code branches, creating pull requests, and performing local quality checks. - [INDIRECT_PROMPT_INJECTION]: The skill instructions create a surface for indirect prompt injection by directing the agent to read and adopt content from an external project file.
- Ingestion points: The
.github/PULL_REQUEST_TEMPLATE.mdfile is used to populate the pull request body. - Boundary markers: Absent; the skill does not specify delimiters or instructions to ignore embedded commands within the template.
- Capability inventory: The agent has access to file system reading, network operations (via
gitandgh), and local shell command execution. - Sanitization: Absent; the workflow assumes the repository's own template file is a trusted source of formatting.
Audit Metadata