tdd-workflow
Pass
Audited by Gen Agent Trust Hub on Oct 6, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest feature requirements and source code, which are potentially untrusted external inputs. These inputs are used to drive the creation of files and the execution of commands (via the test suite), creating a standard surface for indirect prompt injection.
- Ingestion points: Ingests
feature-requirementsandsource-codeas primary inputs (SKILL.md). - Boundary markers: The instructions do not define specific delimiters or instructions for the agent to ignore potentially malicious embedded content within the requirements or source code.
- Capability inventory: The skill explicitly lists the ability to create files and run shell commands (e.g.,
npm test) as part of its workflow (SKILL.md). - Sanitization: No explicit sanitization or validation logic is defined for the input requirements before they are processed by the agent.
Audit Metadata