ohos-app-scaffold
Pass
Audited by Gen Agent Trust Hub on Oct 3, 2026
Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
- [COMMAND_EXECUTION]: The skill uses the
devecoclicommand-line tool to initialize new HarmonyOS projects from templates. It also executes environment verification commands usingnode,npm, anddevecocli -Vto ensure the toolchain is correctly configured in the user's PATH. - [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied parameters to configure the new project, creating a potential attack surface for indirect prompt injection.
- Ingestion points: Project configuration values including
<project-dir>,<AppName>,<com.example.app>, and<level>are sourced from user requests (SKILL.md). - Boundary markers: The instructions do not specify the use of delimiters or specific warnings to the agent to ignore instructions embedded within these configuration strings.
- Capability inventory: The skill has the capability to execute shell commands via the
devecoclitool (SKILL.md). - Sanitization: There is no explicit requirement for the agent to sanitize or validate the user-supplied strings before interpolating them into the CLI command.
Audit Metadata