create-pr-jp
Pass
Audited by Gen Agent Trust Hub on Mar 27, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes
pnpm lintandpnpm testto validate code before creating a pull request. These commands run scripts defined locally within the repository'spackage.jsonfile. - [PROMPT_INJECTION]: The skill features an indirect prompt injection surface by ingesting data from git history and local template files to construct the pull request body.
- Ingestion points: PR templates located at
.github/pull_request_template.mdordocs/pull_request_template.md, as well as output fromgit logandgit diffcommands. - Boundary markers: None identified; content from these files and commands is directly used to generate the PR description.
- Capability inventory: The skill can execute shell commands (
pnpm,git,gh) and perform network operations via the GitHub CLI. - Sanitization: There is no evidence of sanitization or filtering of the content retrieved from git logs or template files before it is processed by the agent.
Audit Metadata