c4-architecture
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes the local codebase to identify architectural elements, creating a surface where malicious instructions embedded in comments or strings could influence the agent's behavior during analysis.\n
- Ingestion points: The workflow in
SKILL.mdinstructs the agent to analyze the local codebase to identify components, containers, and relationships.\n - Boundary markers: The skill does not provide specific instructions or markers to distinguish between legitimate code and potentially malicious embedded prompts during the analysis phase.\n
- Capability inventory: The agent is authorized to write architectural diagrams and documentation to the
docs/architecture/directory.\n - Sanitization: There are no instructions to sanitize or validate descriptive text extracted from the codebase before it is included in the output diagrams.
Audit Metadata