c4-architecture
Pass
Audited by Gen Agent Trust Hub on Feb 17, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- Indirect Prompt Injection (LOW): The skill possesses a surface for indirect prompt injection because it is designed to ingest and interpret data from a local codebase.
- Ingestion points: The 'Analyze codebase' step involves exploring and reading project files to identify system components.
- Boundary markers: The documentation does not specify the use of delimiters or 'ignore' instructions to prevent the agent from obeying commands embedded in source code comments or metadata.
- Capability inventory: The skill has file system read access for analysis and write access to the
docs/architecture/directory. - Sanitization: There is no documented logic for sanitizing or escaping content extracted from the codebase before it is interpolated into diagram generation prompts.
Audit Metadata