c4-architecture
Pass
Audited by Gen Agent Trust Hub on Aug 16, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill's primary function is generating Mermaid diagram syntax for architecture documentation. It does not include any executable scripts or binary files.
- [SAFE]: No hardcoded credentials, sensitive file paths, or network exfiltration patterns were detected. The skill writes documentation to a localized 'docs/architecture/' directory.
- [SAFE]: There is no evidence of obfuscation or hidden instructions. All instructions and references are provided in clear Markdown syntax.
- [INDIRECT_PROMPT_INJECTION]: The skill has a surface for indirect prompt injection as it analyzes codebase files to generate diagrams. Ingestion points: System codebase analysis (SKILL.md, Workflow Step 2); Boundary markers: Not explicitly defined in SKILL.md; Capability inventory: File read access (workspace) and file write access to docs/architecture/ (SKILL.md, Workflow Step 4); Sanitization: No specific sanitization mentioned in SKILL.md. This is inherent to the skill's function and assessed as safe.
Audit Metadata