test-optimize
Pass
Audited by Gen Agent Trust Hub on Oct 12, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process and optimize user-provided test files and source code, which constitutes untrusted data. The execution flow requires the agent to run shell commands to verify the tests, creating a potential path for code execution from malicious files within a user's repository.
- Ingestion points: The agent accesses and reads project files when performing tasks like 'locating risk', 'optimizing assertions', or 'reviewing tests'.
- Boundary markers: The skill lacks explicit instructions or boundary markers to differentiate between user-provided code content and agent instructions, which could lead to instructions embedded in code being misinterpreted.
- Capability inventory: The skill workflow includes a mandatory step to 'Run minimal relevant tests, file-level lint and type checking', granting the agent the capability to execute code provided in the user's project.
- Sanitization: No specific sanitization or verification protocols are provided to ensure that the code being executed is safe or to prevent the execution of malicious scripts embedded in the tests.
Audit Metadata