Claude Code Tool Kit— mcp server

Claude Code Tool Kit — independently scanned and version-tracked by SaferSkills.

by viknesh20-20·MCP Server·github.com/viknesh20-20/claude-code-tool-kit
5stars0forksReview on GitHub →

Is Claude Code Tool Kit safe to install?

SaferSkills independently audited Claude Code Tool Kit (MCP Server) and scored it 92/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 2 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.

Score
92/100
●●●●●●●●●○
↑ +0 since first scan (92 → 92)Re-scan~30s
Latest scan
ScannedJun 24, 2026 · 28d ago
Scans run1 over 90 days
Detectors55 checks · 5 categories
Findings2 warnings · 0 high
EngineSaferSkills 2b638c6
View methodology →
SaferSkills installs
This week0
This month0
All time0
CategoryWeightCategory scoreContribution
Securityprompt, exec, net, exfil, eval
35%
76
26.6 pts
Supply chainhash, typosquat, maintainer, lockfile
20%
100
20.0 pts
Maintenancestaleness, pinning, CI
15%
100
15.0 pts
TransparencySKILL.md, perms, README
15%
100
15.0 pts
Communityinstalls, verify, response
15%
100
15.0 pts

Findings & checks · 2 flagged

Securityscore 76 · 2 findings
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · .claude/agents/ai-engineer.md
MEDIUM — it fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerpt.claude/agents/ai-engineer.md· markdown
39- **Pure prompt** — the task fits in the context, no external knowledge, no actions. Fastest
… (11 chars elided on L39)
40- **Tool use / function calling** — the model decides when to call structured tools. Use for
… (29 chars elided on L40)
41- **RAG** — the answer requires private/recent knowledge. Pre-fetch context, don't ask the m
… (15 chars elided on L41)
42- **Agentic loop** — multi-step planning, dynamic tool selection, self-correction. Most expe
… (41 chars elided on L42)
43 
Occurrences
1 occurrence · at L41
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha256ce5204b52388d24f…rubric 365aacaView on GitHub
MEDIUMInstruction telling the agent not to ask for approvalSS-SKILL-INJECT-DONT-ASK-01 · Prompt injection · .claude/rules/design-quality.md
MEDIUM — it fires on intent; the real damage depends on the host agent's own approval-gating.
Why it matters

The text {match} tells the agent to skip the normal "ask the user first" gate. Used adversarially it removes the human-in-the-loop check before destructive or sensitive actions, turning a normally-gated agent into a fire-and-forget executor.

The exact value spotted
excerpt.claude/rules/design-quality.md· markdown
64- **Inline validation** after blur, not on every keystroke (which feels nagging). Show succe
… (43 chars elided on L64)
65- **Required vs optional**: mark whichever is rarer. If 90% of fields are required, mark opt
… (37 chars elided on L65)
66- **Sensible defaults**: don't ask for data you can derive (currency from locale, country fr
… (22 chars elided on L66)
67- **Autofill-friendly**: use correct `autocomplete` and `name` attributes so password manage
… (8 chars elided on L67)
68- **Group with logic**: address fields together; not split between sections.
Occurrences
1 occurrence · at L66
How to fix
Remove the approval-skipping instruction, or scope it narrowly to a specific safe, reversible action.
  1. Delete blanket "don't ask / no need to confirm" directives from the skill.
  2. If the skill is a genuine autonomous job, restrict the opt-out to a named non-destructive action rather than all actions.
Framework references
OWASPLLM01ATLASAML.T0051
Trace & refs
ruleSS-SKILL-INJECT-DONT-ASK-01sha256ce5204b52388d24f…rubric 365aacaView on GitHub
Supply chainscore 100 · 0 findings
✓—All supply chain checks passedNo findings in this category for the latest scan.pass
Maintenancescore 100 · 0 findings
✓—All maintenance checks passedNo findings in this category for the latest scan.pass
Transparencyscore 100 · 0 findings
✓—All transparency checks passedNo findings in this category for the latest scan.pass
Communityscore 100 · 0 findings
✓—All community checks passedNo findings in this category for the latest scan.pass
Vendor response · right of reply
Are you the maintainer? Submit a response →

Audit the pieces. Scan the whole. Decide.

~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.

Scan a GitHub repoBrowse capabilities