architect-analyze
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill executes local bash scripts (
setup-architect.shandmermaid-lint.sh) for environment setup and diagram validation. These are provided by the vendor (tikalk) as part of the architecture toolset. - [INDIRECT_PROMPT_INJECTION]: The skill processes external Markdown documents and user input, creating a surface for indirect prompt injection.
- Ingestion points:
$ARGUMENTSand architecture artifacts (AD.md,adr/*.md). - Boundary markers: Not present.
- Capability inventory: Shell script execution.
- Sanitization: Not present.
Audit Metadata