wraps-quickstart

Pass

Audited by Gen Agent Trust Hub on Jul 21, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses shell commands to detect project context, including cat package.json | grep to identify frameworks and ls to check for hosting configurations. It also runs aws sts get-caller-identity to verify the presence of AWS credentials.
  • [EXTERNAL_DOWNLOADS]: The instructions direct the agent to download and execute the vendor's CLI tool using npx @wraps.dev/cli@latest and install the @wraps.dev/email SDK. These resources originate from the vendor's own namespace.
  • [INDIRECT_PROMPT_INJECTION]: The skill ingests data from local files like package.json to adapt its guidance. While this presents an ingestion surface for untrusted data, the use of targeted grep patterns limits the risk of instruction leakage from the files being analyzed.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 21, 2026, 11:31 AM
Security Audit — agent-trust-hub — wraps-quickstart