git-upstream-pr
Pass
Audited by Gen Agent Trust Hub on Mar 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes multiple shell commands using
gitand the GitHub CLI (gh) to perform repository operations, such as branching, stashing, and pushing changes. - [PROMPT_INJECTION]: The skill has an indirect prompt injection surface because it uses data from commit messages to populate command arguments.
- Ingestion points: Git commit history retrieved via
git login Step 3 and user-provided descriptions viaAskUserQuestionin Step 5. - Boundary markers: No specific delimiters are defined to isolate untrusted commit data from command logic.
- Capability inventory: The skill is authorized to perform
git commit,git push, andgh pr createoperations. - Sanitization: There is no explicit instruction to sanitize or escape commit titles or descriptions before they are used in shell commands.
Audit Metadata