testing-setup-shared
Pass
Audited by Gen Agent Trust Hub on Nov 10, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill instructs the agent on executing local shell commands via the NX build system (e.g.,
npx nx test) for running unit and integration tests and generating coverage reports.\n- [INDIRECT_PROMPT_INJECTION]: The skill logic requires reading and analyzing user-provided source files to determine the correct testing environment and mocking pattern. This represents a potential surface for indirect prompt injection where malicious instructions could be embedded within the files being processed.\n - Ingestion points: External source code files identified by the user in Step 1.1.\n
- Boundary markers: Absent; the skill does not specify the use of delimiters or instructions for the agent to ignore potentially malicious content within the ingested files.\n
- Capability inventory: The skill utilizes file system write capabilities (
touchcommand in Step 2.3) and shell command execution via NX (npx nx testin Step 7.1).\n - Sanitization: Absent; the skill does not describe any validation or sanitization of the content from the source files before it is processed by the agent.
Audit Metadata