work-ship
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill frequently constructs and executes shell commands using external tools like
git,gt(Gitea/Forgejo CLI), and custom environment scripts (df-gt-*). These commands include destructive actions likegit pushand repository state changes throughgt pr createandgt apiPOST requests. - [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data which could potentially contain malicious instructions intended to influence the agent's behavior during the shipping process.
- Ingestion points: The skill reads branch names (Step 1) and pull request review comments (Step 1 and Step 5) from external sources.
- Boundary markers: There are no explicit delimiters or instruction-ignore warnings defined when processing the branch names or review data.
- Capability inventory: The skill has significant capabilities, including pushing code to remote repositories (
git push), creating/editing pull requests (gt pr edit), and making arbitrary API requests to the repository host (gt api). - Sanitization: The skill does not define any sanitization or validation steps for the branch names or PR data before using them to drive logic or command construction.
Audit Metadata