skills/alibaba/druid/openspec-onboard/Gen Agent Trust Hub

openspec-onboard

Pass

Audited by Gen Agent Trust Hub on Oct 15, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses standard shell commands including openspec, git, and mkdir to manage project state and automate the creation of documentation artifacts. These operations are essential for its purpose and restricted to the project directory.
  • [DATA_EXPOSURE]: It reads local source files to detect TODO comments and other improvement opportunities to suggest tasks to the user. This data remains within the local environment and is not transmitted externally.
  • [INDIRECT_PROMPT_INJECTION]: The skill processes existing codebase content which could theoretically contain instructions intended to influence the agent. However, this is a standard risk for development tools and is mitigated by the skill's local scope and the user's supervision during the interactive tutorial.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 15, 2026, 12:45 AM