scaffold-gateables
Pass
Audited by Gen Agent Trust Hub on Oct 23, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted project data to determine its implementation logic, creating a surface where malicious instructions in the analyzed code could influence the agent's behavior.
- Ingestion points: The skill reads
package.json,progress.md, and core source files such asConstants.js,EventBus.js,GameState.js, andmain.jsto understand the game's architecture. - Boundary markers: No specific delimiters or instructions to ignore embedded commands are present in the file analysis phase.
- Capability inventory: The skill performs file system operations including creating new modules (e.g.,
Entitlements.js,SkinPicker.js) and modifying existing core game logic. - Sanitization: There is no explicit sanitization or validation of the input read from the external project files before it is processed for code generation.
Audit Metadata