tdd
Pass
Audited by Gen Agent Trust Hub on Oct 16, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [SAFE]: The skill provides a standard procedural workflow for TDD, which includes writing failing tests to verify bug reproduction and subsequent fixes.\n- [SAFE]: References to external code repositories are for attribution and licensing purposes, linking to public projects on GitHub.\n- [SAFE]: The skill mentions the library
@overextended/ox_lib, which is a development resource associated with the author's organization.\n- [COMMAND_EXECUTION]: The instructions describe the use of common development tools, such as the TypeScript compiler (tsc), for regression testing purposes.\n- [INDIRECT_PROMPT_INJECTION]: The workflow requires the agent to ingest user-provided code and bug reports, creating a surface for potential indirect prompt injection.\n - Ingestion points: TypeScript resources and bug descriptions supplied by the user during the TDD process.\n
- Boundary markers: The instructions do not specify any delimiters to isolate the untrusted user data.\n
- Capability inventory: The methodology makes use of test runners and compiler tools to execute and verify code.\n
- Sanitization: No specific sanitization or validation routines are defined for the ingested code or reports.
Audit Metadata