ship-now
Pass
Audited by Gen Agent Trust Hub on Aug 24, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
gh pr merge --admincommand to bypass branch protection rules, such as required status checks and minimum review counts. This allows merging into protected branches by overriding repository-level safety constraints.- [PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it incorporates external feedback into its decision-making process. - Ingestion points: GitHub PR review summaries and comments from humans or bots (SKILL.md, Workflow Step 2).
- Boundary markers: Absent. The instructions do not specify delimiters or warnings to ignore instructions embedded in the comments.
- Capability inventory: The agent can execute local
pnpmcommands, perform git operations, and carry out administrative merges. - Sanitization: Absent. The agent is instructed to read and respond to all feedback without filtering or sanitizing the input for malicious instructions.
Audit Metadata