ns-e2e-tests
Pass
Audited by Gen Agent Trust Hub on Oct 24, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data from the repository's source code and task-specific markdown files to determine testing requirements and generate code.
- Ingestion points: Scans
frontend/files for routes, forms, and API usage, and references task-specific markdown files (e.g.,task-*.md) for data-testid contracts. - Boundary markers: The instructions lack explicit requirements for using delimiters or warnings to separate external data from agent instructions.
- Capability inventory: The skill performs file reads and writes and triggers shell commands via the project's package manager.
- Sanitization: There is no documented process for sanitizing or validating content retrieved from external files before it is processed by the agent.
- [COMMAND_EXECUTION]: The skill involves the execution of shell commands, specifically
npm run cypress:run(or its Docker equivalent), to perform end-to-end tests. While this is the intended functionality, it relies on scripts defined in apackage.jsonfile which could potentially be modified to include malicious instructions.
Audit Metadata