Back to skill

Security audit

n8n-builder

Security checks for vulnerabilities and agentic risk

Overview

This workflow builder needs review because its default instructions activate live automations without clearly requiring your authorization for their ongoing effects.

Use a test n8n instance and a narrowly scoped API key, with HTTPS for remote connections. Require your authorization before activating each workflow after reviewing its triggers, connected accounts, recipients, and data changes. Check what chat or lead information reaches OpenAI, Google Sheets, and Slack. All bundled files were inspected to investigate scanner gaps; live server behavior and permissions were not tested.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Findings (28)

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 18)May include surrounding context.

md
SON following the schema in `references/workflow-schema.md`. Use patterns from `references/workflow-patterns.md` as templates.

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 59)May include surrounding context.

md
For complete workflow examples (webhook, schedule, AI agent, DB sync, error handling) → read `references/workflow-patterns.md`

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 20)May include surrounding context.

md
3. **Deploy via API** — Use `scripts/n8n-api.sh create <file>` or pipe JSON to `scripts/n8n-api.sh create-stdin`.

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 22)May include surrounding context.

md
4. **Activate** — Use `scripts/n8n-api.sh activate <workflow_id>` for trigger-based workflows.

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 24)May include surrounding context.

md
5. **Verify** — List workflows to confirm deployment: `scripts/n8n-api.sh list`.

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 30)May include surrounding context.

md
scripts/n8n-api.sh list

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 33)May include surrounding context.

md
scripts/n8n-api.sh create /tmp/workflow.json

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 36)May include surrounding context.

md
echo '{"name":"Test",...}' | scripts/n8n-api.sh create-stdin

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 39)May include surrounding context.

md
scripts/n8n-api.sh get <id>

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 40)May include surrounding context.

md
scripts/n8n-api.sh activate <id>

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 41)May include surrounding context.

md
scripts/n8n-api.sh deactivate <id>

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 42)May include surrounding context.

md
scripts/n8n-api.sh delete <id>

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 43)May include surrounding context.

md
scripts/n8n-api.sh execute <id>

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 46)May include surrounding context.

md
scripts/n8n-api.sh credentials

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 47)May include surrounding context.

md
scripts/n8n-api.sh tags

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 69)May include surrounding context.

md
- **Credentials** must exist in n8n before activation — check with `scripts/n8n-api.sh credentials`

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 70)May include surrounding context.

md
- **Test before activating** — use `scripts/n8n-api.sh execute <id>` for manual trigger workflows

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

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.

The workflow instructs the agent to activate trigger-based automations without warning about live side effects.

Medium
Category
Output Handling
Confidence
93% confidence
Finding

The default workflow proceeds from deployment to activation without distinguishing permission to create a workflow from permission to run it against live services. In this skill's context, activation can enable recurring messages, database changes, or externally callable workflows, causing unintended ongoing effects even when the user only requested construction.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/workflow-patterns.md (reported line 77)May include surrounding context.

md
"typeVersion": 4.2,
      "position": [450, 300],
      "parameters": {
        "url": "https://api.example.com/data",
        "method": "GET"
      }
    },

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/workflow-patterns.md (reported line 298)May include surrounding context.

md
"typeVersion": 4.2,
      "position": [450, 300],
      "parameters": {
        "url": "https://api.example.com/fragile",
        "options": { "timeout": 10000 }
      },
      "continueOnFail": true

The AI-agent workflow forwards incoming chat messages to OpenAI without a privacy warning.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

The workflow uses the incoming request's body.message as the agent input and connects the agent to an OpenAI model. The surrounding description does not warn that user messages will be transmitted to an external provider or advise against sending sensitive content.

Content

No source excerpt is available for this finding.

The database-sync workflow exports lead information to Google Sheets and Slack without a privacy warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The workflow constructs lead names and phone numbers, routes the transformed records to a Google Sheets append operation, and posts lead names to Slack. Although the description mentions multiple destinations, it does not warn that personal information leaves the source database and becomes accessible through the destination spreadsheet and channel.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/n8n-api.sh (reported line 43)May include surrounding context.

sh
curl -s -H "$AUTH_HEADER" "$BASE/workflows/$2" | jq .
    ;;
  create)
    curl -s -X POST -H "$AUTH_HEADER" -H "Content-Type: application/json" \
      -d @"$2" "$BASE/workflows" | jq .
    ;;
  create-stdin)

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/n8n-api.sh (reported line 47)May include surrounding context.

sh
-d @"$2" "$BASE/workflows" | jq .
    ;;
  create-stdin)
    curl -s -X POST -H "$AUTH_HEADER" -H "Content-Type: application/json" \
      -d @- "$BASE/workflows" | jq .
    ;;
  update)