test-skill
Pass
Audited by Gen Agent Trust Hub on May 16, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent to execute shell commands using
pnpm test. This is used to verify the generated tests and check code coverage. While this is the intended functionality of a testing skill, it involves executing local code and scripts. - [PROMPT_INJECTION]: This skill possesses an indirect prompt injection surface as it processes untrusted source code to generate unit tests and subsequently executes those tests.
- Ingestion points: The skill reads source code files from the project directory (e.g.,
packages/,projects/app/src/) to understand the logic for test generation. - Boundary markers: No explicit boundary markers or instructions to ignore embedded prompts in source files are defined.
- Capability inventory: The agent can execute shell commands via
pnpm testas described in the '常用命令' (Common Commands) section of SKILL.md. - Sanitization: There is no mention of sanitization or validation of the content of the source files before they are processed or used to generate executable test code.
Audit Metadata