shipping-code
Pass
Audited by Gen Agent Trust Hub on Jun 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill invokes several local command-line tools for build verification and version control, including
git,cargo(for Rust projects),npx(executingeslintandtscfor TypeScript projects), and a project-specific tool namedtraderfor migration verification. - [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes data from
git diff, which represents an untrusted ingestion point. - Ingestion points: Staged code changes are read via
git diff --cachedcommands inSKILL.md. - Boundary markers: None identified. The instructions do not specify delimiters or provide warnings to the agent to ignore instructions embedded within the code being analyzed.
- Capability inventory: The skill has the capability to execute shell commands such as
git commit,cargo build(which can run arbitrary code via build scripts), andnpxcommands. - Sanitization: No sanitization or filtering is applied to the content of the diffs before they are processed by the agent.
Audit Metadata