pr
Pass
Audited by Gen Agent Trust Hub on Aug 25, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from the repository's git history and configuration files.
- Ingestion points:
scripts/gather-pr-context.shreads git logs, diffs, and PULL_REQUEST_TEMPLATE.md files into the agent's context. - Boundary markers: Instructions do not provide explicit delimiters or warnings to ignore embedded instructions in the processed diffs or templates.
- Capability inventory: The skill uses the Bash tool to execute
git pushandgh pr create/editcommands. - Sanitization: The skill mitigates risks by requiring explicit user approval via
AskUserQuestionbefore executing any sensitive shell commands like pushing to a remote or creating a PR.
Audit Metadata