master-react-coding-orchestrator
Pass
Audited by Gen Agent Trust Hub on Sep 21, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill treats external data as authoritative and "sacred law," creating a vulnerability where malicious instructions embedded in processed data could influence code generation and file system operations.
- Ingestion points: The skill ingests untrusted data from
.SS_WF/Agent/Analysis/{{ticket_id}}_ANALYSIS_PLAN.md,figma-output/responsive_design_intent.json, and other Figma context files. - Boundary markers: There are no explicit boundary markers or instructions to ignore embedded instructions in the ingested data. In contrast, the skill is instructed that developer notes in the analysis plan "override all other sources at every decision point."
- Capability inventory: The skill possesses extensive file-writing capabilities, invoking tools to create React components, logic, Sitecore wiring, and test files across the repository (Phases 4 through 9).
- Sanitization: No sanitization, escaping, or validation of the content within the analysis plan or Figma outputs is specified before it is incorporated into source code generation.
Audit Metadata