swe-test-integration-test-writer

Pass

Audited by Gen Agent Trust Hub on Sep 17, 2026

Risk Level: SAFECOMMAND_EXECUTIONDYNAMIC_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill ingest project source code, configuration files, and directory structures to understand the application stack and generate relevant tests. This processing of untrusted external data creates a potential surface for indirect prompt injection.
  • Ingestion points: The agent uses ReadFile and ListDirectory to scan the project files (Step 1).
  • Boundary markers: There are no explicit instructions or delimiters defined to prevent the agent from following instructions that might be embedded in the code it is analyzing.
  • Capability inventory: The skill has access to RunCommand for executing tests and migrations, and WriteFile for creating new files.
  • Sanitization: The instructions do not specify any sanitization or validation of the input code before it is used to generate test files or command arguments.
  • [COMMAND_EXECUTION]: The instructions guide the agent to use the RunCommand tool to execute shell commands such as npx vitest run, npx jest, and Prisma migration commands (Step 7). These are standard development workflows intended to verify test suite functionality.
  • [DYNAMIC_EXECUTION]: The skill provides templates and reference code (e.g., in references/testcontainers-and-docker.md) that use child_process.execSync to trigger database migrations during test setup. While these are examples for the user's project, the agent is tasked with generating these files, which involves producing code that performs dynamic execution.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 17, 2026, 03:21 AM
Security Audit — agent-trust-hub — swe-test-integration-test-writer