skills/celeroncoder/skills/native-sdk/Gen Agent Trust Hub

native-sdk

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill guides users to install the @native-sdk/cli package from the public NPM registry as part of the initial setup.
  • [COMMAND_EXECUTION]: The skill utilizes the native command-line tool to initialize projects (native init), manage development servers (native dev), and retrieve specialized skill modules via the CLI.
  • [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and follow instructions fetched at runtime via the native skills get command suite.
  • Ingestion points: Reference documentation, implementation guides, and orientation content retrieved from native skills get core, native skills get automation, and native skills get zig commands.
  • Boundary markers: No specific delimiters or warnings to ignore embedded instructions are present in the discovery stub.
  • Capability inventory: The skill is scoped to execute subcommands of the native CLI tool and the @native-sdk/cli package via npx.
  • Sanitization: Content is retrieved through the SDK's own command-line utility, representing standard documentation delivery for the toolkit.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 03:56 PM
Security Audit — agent-trust-hub — native-sdk