Architecture Patterns
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFECOMMAND_EXECUTION
Full Analysis
- [COMMAND_EXECUTION]: The skill utilizes several local bash scripts to perform file system operations. These include
create-architecture.shfor project scaffolding,validate-mermaid.shfor syntax checking, andexport-diagrams.shfor content extraction. All scripts operate on user-specified paths and perform their documented functions without suspicious side effects. - [INDIRECT_PROMPT_INJECTION]: The skill processes external markdown files via the validation and export scripts, creating a surface for indirect prompt injection.
- Ingestion points: Markdown files passed to
validate-mermaid.shorexport-diagrams.shin thescripts/directory. - Boundary markers: None present.
- Capability inventory: File system writes and directory creation in the user's project path.
- Sanitization:
export-diagrams.shperforms character filtering usingtr -cd '[:alnum:]-'on generated filenames to prevent path traversal. - [SAFE]: No instances of prompt injection, data exfiltration, obfuscation, or remote code execution were found. The skill's behavior is entirely consistent with its stated purpose of assisting with architecture documentation.
Audit Metadata