sparkscan-capacitor
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [SAFE]: The skill provides official documentation and integration code for the Scandit SDK. All external links point to official Scandit domains (docs.scandit.com) or repositories (github.com/Scandit).\n- [INDIRECT_PROMPT_INJECTION]: The skill identifies a surface for indirect prompt injection by reading local project files.\n
- Ingestion points: The agent is instructed to read
package.json, lockfiles (package-lock.json,yarn.lock), and source code files (e.g.,app.js,main.ts).\n - Boundary markers: No specific delimiters or "ignore embedded instructions" warnings are used when processing these files.\n
- Capability inventory: The skill's primary purpose is to write/modify files and suggest CLI commands (
npm install,npx cap sync).\n - Sanitization: The instructions emphasize strict adherence to provided API references to prevent arbitrary code generation.\n- [SAFE]: Secret handling instructions follow security best practices. The skill uses placeholders for license keys, requires masking when displaying keys in chat, and explicitly forbids searching project files or the environment for sensitive credentials.
Audit Metadata