create-pull-request
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes potentially untrusted data that could influence the agent's behavior or the parameters of executed commands.
- Ingestion points: Commit messages (via
git log), branch names, and the contents of a local pull request template (.github/pull_request_template.md) are read into the agent's context. - Boundary markers: The instructions do not define clear delimiters or include warnings to ignore instructions embedded within the commit messages or templates during processing.
- Capability inventory: The skill has the capability to execute shell commands via the
ghCLI (gh pr create) andgit(git push), and to perform network operations against GitHub. - Sanitization: The skill lacks explicit instructions for the agent to sanitize or escape data extracted from commits or templates before using them as arguments (
--title,--body) in shell commands. - [COMMAND_EXECUTION]: The skill relies on the execution of multiple CLI commands including
gitand the GitHubghtool. While these are standard tools, they are executed with arguments derived from external project data.
Audit Metadata