shipit
Pass
Audited by Gen Agent Trust Hub on Jul 7, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses shell commands including git, GitHub CLI (gh), and package managers (npm, pnpm, bun) to automate repository workflows like merging PRs, committing code, and running local scripts.
- [PROMPT_INJECTION]: The skill possesses an attack surface for indirect prompt injection where malicious instructions could be embedded in the data the skill processes.
- Ingestion points: Untrusted data enters the agent context through the output of 'git status', 'git diff', 'gh pr view', and the content of 'notes/session-log.md'.
- Boundary markers: No explicit delimiters or instructions to ignore instructions embedded in the ingested data were identified.
- Capability inventory: The skill is capable of performing sensitive repository actions including merging pull requests and pushing directly to the main branch.
- Sanitization: No sanitization or validation of the ingested project metadata or file content is performed before it is used to influence agent behavior.
Audit Metadata