arkts-static-spec
Pass
Audited by Gen Agent Trust Hub on Jun 13, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of markdown documentation files (
spec/*.mdandcookbook/*.md) and configuration files. It provides reference material for the ArkTS programming language, including syntax rules, type systems, and migration guides. - [NO_CODE]: The skill does not include any executable scripts (Python, JavaScript, Bash) or binary dependencies. The code snippets provided in the documentation are illustrative examples for the user and are not intended for execution by the agent.
- [COMMAND_EXECUTION]: No shell command patterns or dynamic context injection sequences (
!command) were found in the instructions. - [DATA_EXFILTRATION]: There are no network requests, hardcoded credentials, or attempts to access sensitive system files. The only external URL mentioned is a benign example (
https://example.com) in the concurrency documentation. - [PROMPT_INJECTION]: The instructions in
SKILL.mdemphasize grounding the agent's responses in the provided documentation (e.g., "strictly follow skill document content"). These are standard safety and accuracy constraints and do not attempt to bypass system filters or override core agent behavior.
Audit Metadata