test-case
Pass
Audited by Gen Agent Trust Hub on Jul 30, 2026
Risk Level: SAFECOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses
pnpm testcommands to verify code and check coverage, which is the primary and expected function of the tool within the project's local workspace. - [PROMPT_INJECTION]: The skill processes source code files to generate tests, identifying an indirect prompt injection surface.
- Ingestion points: It reads source code from the
packages/andprojects/directories. - Boundary markers: The instructions do not provide specific delimiters or ignore-instructions for the processed code.
- Capability inventory: The agent can execute shell commands via
pnpmand create/modify testing files. - Sanitization: There is no explicit requirement for the agent to sanitize or validate the source code before processing.
Audit Metadata