openharmony-build

Pass

Audited by Gen Agent Trust Hub on Sep 16, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill is primarily designed to execute shell commands and bundled scripts to manage the OpenHarmony build process. This includes running ./build.sh, hb build, and several diagnostic scripts (analyze_build_error.sh, check_fast_rebuild.sh, etc.) to facilitate compilation and log analysis.
  • [INDIRECT_PROMPT_INJECTION]: The skill performs analysis on build logs (build.log) which are generated during the compilation process. These logs could potentially contain data from external dependencies or build artifacts that might influence the agent's reasoning. The skill mitigates this by using structured diagnostic scripts and providing clear instructions for the agent to verify failures against the primary log rather than relying solely on terminal output.
  • [PRIVILEGE_ESCALATION]: Documentation in references/common-errors.md mentions commands using sudo (e.g., sudo dpkg-reconfigure dash, sudo fallocate) as manual solutions for environment issues. The skill does not instruct the agent to execute these automatically and includes specific constraints in SKILL.md requiring user consent before performing environment bootstrap or setup tasks.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 16, 2026, 02:24 AM