antd-mobile-release

Pass

Audited by Gen Agent Trust Hub on Oct 13, 2026

Risk Level: SAFECOMMAND_EXECUTIONEXTERNAL_DOWNLOADSINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill executes multiple repository management and build commands as part of the release cycle.
  • Evidence: Commands include pnpm build, pnpm package-diff, npm pack --dry-run, git commit, git push, and git tag.
  • Context: These operations are consistent with the skill's purpose and are targeted at the official ant-design-mobile repository.
  • [EXTERNAL_DOWNLOADS]: The skill downloads external project dependencies to prepare the build environment.
  • Evidence: The skill runs pnpm install based on the repository's lock file.
  • Context: This is a standard and expected step for Node.js-based release automation within a vendor's own repository.
  • [INDIRECT_PROMPT_INJECTION]: The skill summarizes external pull request (PR) data to create release logs, which introduces a potential injection surface.
  • Ingestion points: The skill reads PR links and change descriptions from GitHub history to generate release notes.
  • Boundary markers: The instructions do not specify the use of delimiters or specific warnings to ignore instructions embedded in the PR data.
  • Capability inventory: The agent has permissions to execute git push, create tags, and create GitHub Releases.
  • Sanitization: There is no explicit requirement to sanitize or escape retrieved PR content before it is included in the release logs or presented to the user.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 13, 2026, 02:43 AM