git-guardrails-claude-code
Verdict safe, but 1 finding (1 info), mainly policy violation. Most recent scan 2026-10-22.
Second scanner: NVIDIA SkillSpector
The two scanners disagree: Cisco found nothing and SkillSpector says do not install. One of them has a blind spot here; read the skill before trusting either. How the two scanners compare across the whole corpus: Two scanners, one corpus.
What this skill does
Set up Claude Code hooks to block dangerous git commands (push, reset --hard, clean, branch -D, etc.) before they execute. Use when user wants to prevent destructive git operations, add git safety hooks, or block git push/reset in Claude Code.
- Package
- 3 files, 2.9 KB
- SKILL.md
- 257 words, 8 sections
- Code
- Shell (1)
SKILL.md covers: Setup Git Guardrails · What Gets Blocked · Steps · 1. Ask scope · 2. Copy the hook script · 3. Add hook to settings · 4. Ask about customization · 5. Verify
Findings
INFO Skill does not specify a license Policy Violationstatic
Skill manifest does not include a 'license' field. Specifying a license helps users understand usage terms.
SKILL.md
What is in the package
| File | Kind | Size |
|---|---|---|
SKILL.md | doc | 2.3 KB |
agents/openai.yaml | config | 112 B |
scripts/block-dangerous-git.sh | script | 507 B |
Environment variables referenced
CLAUDE_PROJECT_DIR
Package contents recorded 2026-10-22 at commit 5beb35b040e3. The scan above ran against the version current at scan time; the two can differ if the skill has since been updated.
What we checked
- Static analyzer. Pattern rules over SKILL.md and bundled files: known-bad commands, exfiltration URLs, secrets, obfuscation.
- Bytecode analyzer.
- Pipeline analyzer.
- Correlation analyzer.
- Behavioral analyzer. Checks what the skill asks the agent to do against what its description claims it does.
- Trigger analyzer. Looks for instructions that fire on conditions the user did not ask for.
What we did not check
- Runtime behaviour. The skill was not executed; findings come from reading its files.
- Anything fetched at install or run time, including remote scripts, package dependencies, and URLs the skill tells the agent to open.
- Content the analyzers cannot read: images, binaries, and some non-English text.
- Known scanner bypass classes. See the methodology and limitations page.
Sources
- Repository: https://github.com/mattpocock/skills
- Raw scan result: mattpocock-skills-skills-misc-git-guardrails-claude-code-scan.json
- Badge for your README:
- Request a re-scan