barcode-capture-capacitor
Pass
Audited by Gen Agent Trust Hub on Oct 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill implements event listeners (
didScan) that ingest data directly from scanned barcodes. This constitutes an entry point for untrusted external data. If this data is subsequently passed to an LLM without proper sanitization, it could be used for indirect prompt injection attacks. However, the provided examples focus on logging and UI updates, which is standard behavior for this type of tool. - [COMMAND_EXECUTION]: The instructions include standard development commands such as
npx cap syncandnpm install. These are necessary for the Capacitor framework and the plugin's native synchronization process and do not represent malicious intent. - [CREDENTIALS_SAFE]: The skill provides a structured process for managing API license keys using dedicated MCP tools (
get_license_key,list_license_keys). It explicitly instructs the agent to mask these keys in the chat interface and prohibits searching the local environment or project files for secrets, adhering to strong security practices.
Audit Metadata