senior-architect
Pass
Audited by Gen Agent Trust Hub on Nov 13, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill utilizes automated scanning scripts that read and process the contents of external project files, which introduces an indirect prompt injection surface.
- Ingestion points: The architecture_diagram_generator.py, dependency_analyzer.py, and project_architect.py scripts utilize Path.read_text() to ingest code from a user-specified project directory.
- Boundary markers: The skill does not implement delimiters or safety warnings to isolate the ingested codebase content from the agent's instruction set.
- Capability inventory: The toolset provides automated reporting on structural patterns, dependency coupling, and diagram generation, which are then used by the agent to inform architectural decisions.
- Sanitization: The scripts perform regex extraction for structural metadata but do not sanitize or filter potential natural language instructions embedded within the ingested source code comments or strings.
Audit Metadata