tdd
Pass
Audited by Gen Agent Trust Hub on Sep 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill instructs the agent to read project-specific files like
CONTEXT.mdand Architecture Decision Records (ADRs) to align with the project's domain language. While this is standard behavior for a development tool, it creates a surface where external file content could influence agent instructions.\n - Ingestion points: Reads
CONTEXT.mdand ADRs from the workspace.\n - Boundary markers: No specific delimiters or safety warnings are provided for these inputs.\n
- Capability inventory: The skill operates in a context where code writing and tool execution (like
codebase-design) are expected.\n - Sanitization: No sanitization is specified for the ingested content.
Audit Metadata