tsg-flow-domain-creator
Pass
Audited by Gen Agent Trust Hub on Sep 20, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted input from files like
vision.md,context/domain-map.md, andbacklog/capabilities.md, which could potentially contain malicious instructions. - Ingestion points: content is extracted from project documentation files during the workflow (Step 1 and Step 2).
- Boundary markers: the skill uses a rigid markdown template (
templates/domain-template.md) for output, which provides structural constraints, though it lacks explicit delimiters for untrusted input. - Capability inventory: the skill performs file read operations on context files and file write operations to create documentation and update
flow-state.json. - Sanitization: there is no explicit instruction to sanitize or filter input text before it is interpolated into the generated output.
Audit Metadata