skills/mui/mui-public/mui-release/Gen Agent Trust Hub

mui-release

Pass

Audited by Gen Agent Trust Hub on Aug 13, 2026

Risk Level: SAFE
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill relies on reading external documentation from the target repository to guide the release process.
  • Ingestion points: The skill ingests instructions from scripts/README.md and content from CHANGELOG.md within the target repository.
  • Boundary markers: The skill explicitly designates the repository's scripts/README.md as the authoritative source of truth, though it does not define specific prompt delimiters for this content.
  • Capability inventory: The skill utilizes git for version control, gh (GitHub CLI) for PR management, npm for version verification, and pnpm for running local project scripts.
  • Sanitization: No explicit sanitization of repository documentation is performed; however, this is standard behavior for a release management tool operating on a trusted local codebase.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 13, 2026, 05:21 AM
Security Audit — agent-trust-hub — mui-release