jackin-create-pr
Pass
Audited by Gen Agent Trust Hub on Aug 13, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses several command-line tools to perform its tasks, including
gitfor branch and commit management,gh(GitHub CLI) for PR creation and viewing, andcargo xtaskfor generating the PR body content. These are standard developer tools and are used here within the context of the repository workflow. - [INDIRECT_PROMPT_INJECTION]: The skill represents a surface for indirect prompt injection because the agent is instructed to read file diffs and the output of local commands to generate prose for the pull request. If the code being reviewed contains malicious instructions, the agent might inadvertently follow them while drafting the PR description.
- Ingestion points: The agent reads the 'change digest' from
cargo xtaskstderr, the file diffs of uncommitted changes, and the output ofgh pr view. - Boundary markers: No specific boundary markers or 'ignore' instructions are provided to delimit untrusted data from the agent's instructions.
- Capability inventory: The skill can execute shell commands (
git,gh,cargo), write to the file system (/tmp/pr-body.md), and interact with GitHub APIs. - Sanitization: There is no evidence of sanitization or escaping of the content read from the diffs or tool outputs before it is used to generate the PR prose.
Audit Metadata