Back to skill

Security audit

designer

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious mainly because its guidance for interactive testing lacks safeguards for live user data; some referenced files and security checks were only partially analyzed.

Consider the suspicious verdict before installing. In particular, check whether interactive testing is limited to a sandbox with synthetic data and whether consequential actions require approval. Because analysis was partial, the scan cannot establish that all referenced content and scripts are safe.

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Vulnerability Patterns
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • System Prompt LeakageDirect Leakage, Indirect Extraction, Tool-Based Exfiltration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (8)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 8)May include surrounding context.

md
hot. This skill gives you a brand law, a quality floor, a mechanical detector (`scripts/detect.mjs`), and a verb for every kind of design work.

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 72)May include surrounding context.

md
`node scripts/detect.mjs [--json] [--list-rules] [--scope …] <files…>` — zero-dependency, local, offline. Exit 0 clean / 2 findings / 1 error. Every finding mus

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.

md
| `doctor` | utility | Project drift report (read-only) | `node scripts/context.mjs --doctor` |

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

md
3. `node scripts/context.mjs --doctor` when it exists — treat its output as a **report**. Never repair drift as a side effect of a design task; name it and move

Direct Prompt Extraction

High
Category
System Prompt Leakage
Confidence
85% confidence
Finding

Skill contains instructions that could directly expose system prompts, internal rules, or hidden instructions to users or external parties.

Content

Scanner excerpt · scripts/detect.mjs (reported line 1657)May include surrounding context.

js
// ---------------------------------------------------------------------------

function activeRulesFor(opts) {
  return RULESET.rules.filter((r) => {
    if (r.status !== 'v1-source') return false;
    if (opts.scope === 'css' || opts.scope === 'html') {
      if (!r.scopes.includes(opts.scope)) return false;

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Interactive testing is required without warning about effects on live user data.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The playbook directs an agent to click through workflows and enter worst-case data without restricting testing to a sandbox or requiring approval for consequential actions. On a live interface, following those directions could alter real records, submit transactions, or trigger notifications; interactive testing is appropriate for frontend work, but its operational boundaries are missing.

Content

No source excerpt is available for this finding.

The everyday phrase "what should I do next?" is an insufficiently scoped activation trigger.

Low
Category
Trigger Abuse
Confidence
97% confidence
Finding

The routing playbook explicitly treats "what should I do next?" as an invocation, although that phrase commonly concerns tasks unrelated to interface design. This activation statement does not require an active designer session or an explicit design-related context; offering a menu rather than executing a verb reduces consequences but does not resolve the trigger ambiguity.

Content

No source excerpt is available for this finding.