add-request-protection

Pass

Audited by Gen Agent Trust Hub on Sep 10, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes project manifest files to automate framework detection and configuration, which presents an attack surface where malicious content in these files could influence agent actions.
  • Ingestion points: Reads project configuration files including package.json, bun.lockb, deno.json, pyproject.toml, requirements.txt, and source files like lib/arcjet.ts.
  • Boundary markers: The skill does not employ explicit boundary markers or "ignore instructions" directives when processing these external data sources.
  • Capability inventory: Performs package installations (bun add, pip install), executes system commands via the Arcjet CLI, and modifies local environment (.env) and source code files.
  • Sanitization: No explicit sanitization or validation of data retrieved from project files is described before it is used to determine installation paths or configuration parameters.
  • [EXTERNAL_DOWNLOADS]: The skill installs the Arcjet CLI and framework-specific SDKs from official package registries.
  • Evidence: Instructions include bun add -g @arcjet/cli, pip install arcjet, and various framework adapters such as @arcjet/next and @arcjet/node.
  • [COMMAND_EXECUTION]: The skill utilizes the Arcjet CLI for authentication, site management, and traffic monitoring.
  • Evidence: Usage of arcjet auth login, arcjet sites create, arcjet sites get-key, and arcjet watch.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 10, 2026, 05:25 PM
Security Audit — agent-trust-hub — add-request-protection