api-test-suite-builder
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFECOMMAND_EXECUTIONCREDENTIALS_UNSAFEPROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes shell commands such as
find,grep,sed, andxargsto automate the discovery of API routes in the local project directory. These commands are used as intended for static code analysis and do not involve unauthorized network communication or privilege escalation. - [CREDENTIALS_UNSAFE]: The Python test example in
references/example-test-files.mdcontains the hardcoded stringJWT_SECRET = "test-secret". While this is explicitly documented as a value for a testing environment, hardcoding any secret key in source code files is a violation of security best practices. - [PROMPT_INJECTION]: The skill operates by reading and analyzing local source files to generate test logic, which introduces an attack surface for indirect prompt injection if the ingested code contains adversarial instructions.
- Ingestion points: The agent reads route handler logic from the local filesystem (
.ts,.js,.pyfiles) as specified in the Route Detection section ofSKILL.md. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are used when the agent processes the source code handlers.
- Capability inventory: The agent has the ability to read project files and create new test files on the filesystem.
- Sanitization: The instructions do not define any sanitization or validation steps for the code content before it is used to influence the test generation process.
Audit Metadata