add-guard-protection

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill facilitates the installation of the Arcjet CLI and language-specific SDKs (@arcjet/guard for Node.js, arcjet for Python) from official package registries.
  • [COMMAND_EXECUTION]: The instructions utilize the Arcjet CLI for authentication (arcjet auth login), site management (arcjet sites create), and credential retrieval (arcjet sites get-key). These are standard operations for the tool's intended use.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied messages and external tool outputs to perform security checks. This ingestion of untrusted data represents an attack surface for indirect prompt injection.
  • Ingestion points: Data variables such as message and query passed to the guard() function, as well as returned content from other tools.
  • Boundary markers: No specific delimiters are mandated in the provided code examples for the data passed to the SDK.
  • Capability inventory: The skill utilizes network communication via the Arcjet SDK and shell command execution via the CLI.
  • Sanitization: The skill's primary function is to sanitize and protect inputs using Arcjet's prompt injection and PII detection rules.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 05:25 PM
Security Audit — agent-trust-hub — add-guard-protection