mandu-guard
mandu-guard is a Codebase structure & module boundaries skill for AI agents, published by konamgil in the mandu repository on GitHub. Skillspace rates mandu-guard F (45/100) and the safety scan rated it risky; the rating is based on static analysis only.
Risky. This skill has patterns associated with unsafe behaviour. Read the source carefully before running it.
Architecture guard system for Mandu. Use when checking layer dependencies, enforcing architecture rules, or validating file locations. Triggers on tasks involving architecture, layers, dependencies, or guard commands.
- Grade
- F
- Quality
- 45 / 100
- Safety
- Risky
- GitHub stars
- 46
Unproven: rated by static analysis only, not yet compared head-to-head.
This rating describes the version of the repository we crawled; it may have changed since.
Our review
- Architecture
- 84 / 100
- Maturity
- Packaged: licensed, with a version or references
- Security scan
- High-risk patterns
- License
- MPL-2.0
- Adoption
- Adopted by 0 other repositories, in 0 collections
What the scanner flagged
- executes shell/subprocess
Not checked yet
- Not judged on the rubric yet (not a contender in its category)
- No blind task eval yet
- Scope (portable / vendor / repo-internal) not assessed; only the top of each category is read for scope
- Sibling files (scripts, references) not fetched; security scan covers SKILL.md only
Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.