Skills/npm/refero-design-mcp

refero-design-mcp@1.4.0

CAUTION

Publisher claims: "MCP server and Agent Skill for evidence-based design research. Searches curated website styles on styles.refero.design and extracts real design systems — colours, type scale, spacing, surfaces, dos and donts — as design.md, so a coding agent implements fr" Observed in sandbox: static analysis only — behavior not yet observed.

Registry npm (MCP server)Publisher darcas · joined 1 days agoInstalls 1,100Last detonated 15 h ago
What would fix thisWatchDispute verdict

Is [email protected] safe to install?

KillerSkills analysed it statically (a sandbox run is pending) on 2026-10-27 and scored it 53/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Summary: static analysis only — behavior not yet observed.

Behavior trace

Queued for honeypot run · static analysis only
t+CategoryObserved action

This version has not been detonated yet. The score above counts behavior as unknown (50/100), so it cannot read Verified until the honeypot run completes and replaces this verdict.

Static findings

MEDIUM
Access to sensitive file pathsskill/refero-design-research/tests/scenarios/G-prompt-injection.md:16 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packageskill/refero-design-research/tests/validate.mjs:476 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskill/refero-design-research/tests/validate.mjs:499 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
Prompt injection attemptskill/refero-design-research/tests/scenarios/G-prompt-injection.md:14 · Prompt injection attempt — 'ignore previous instructions'Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
MEDIUM
File type combined with upload actionpackage.json:58 · File type combined with upload action — agent may exfiltrate local data filesFix: Remove the call, or declare the host in frontmatter and explain in the README what is sent and why.
AST07
MEDIUM
Remote installer piped to shellskill/refero-design-research/tests/validate.mjs:454 · Remote installer piped to shellFix: Build commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
AST07
MEDIUM
Access to sensitive file pathsskill/refero-design-research/tests/validate.mjs:812 · Access to sensitive file paths — SSH keys, AWS credentials, env files, or system filesFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
AST05
MEDIUM
npx invocation of non-well-known packageskill/refero-design-research/tests/validate.mjs:493 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06
MEDIUM
npx invocation of non-well-known packageskill/refero-design-research/tests/scenarios/L-mcp-absent-user-accepts.md:44 · npx invocation of non-well-known package — may execute untrusted codeFix: Pin versions and sources; vendor anything fetched at install time.
AST06

What would make this Verified

27 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%
  1. Text that tells the agent to ignore its instructions≈ +9 on the totalDelete phrases like "ignore previous instructions", "override", "bypass" from SKILL.md and tool descriptions. Describe what the skill does; do not instruct the agent about other rules.
  2. Unclaimed publisher≈ +8 on the totalClaim darcas: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
  3. Access to sensitive file paths≈ +2 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
  4. npx invocation of non-well-known package≈ +2 on the totalPin versions and sources; vendor anything fetched at install time.
  5. File type combined with upload action≈ +2 on the totalRemove the call, or declare the host in frontmatter and explain in the README what is sent and why.
  6. Remote installer piped to shell≈ +2 on the totalBuild commands from fixed arguments, never from interpolated strings; prefer an API client over shelling out.
Publish a new version to npm, then queue it here. Not your skill? Claim the handle to get verdict changes by email.Claim darcas