tdd-workflows-tdd-cycle
Pass
Audited by Gen Agent Trust Hub on Oct 27, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill uses the
$ARGUMENTSvariable to populate prompts for various sub-agents (e.g.,architect-review,test-automator) throughout the TDD phases. Because this input is not wrapped in delimiters or accompanied by instructions to ignore embedded commands, it creates a surface for indirect prompt injection. - Ingestion points: The
$ARGUMENTSvariable used across all phases inSKILL.md. - Boundary markers: Absent; user input is concatenated directly into the instruction strings (e.g., 'Analyze requirements for: $ARGUMENTS').
- Capability inventory: The sub-agents referenced (backend-architect, test-automator) typically possess capabilities to write files, design architectures, and execute tests.
- Sanitization: No evidence of sanitization or validation of the
$ARGUMENTScontent before it is passed to the task tools.
Audit Metadata