Back to skill

Security audit

Wiro AI Workflows

Security checks for vulnerabilities and agentic risk

Overview

The verdict is benign because the reported Wiro workflow use appears purpose-aligned, though the scan found a privacy disclosure gap and was only partially complete.

Before installing, consider whether you are comfortable sending workflow text and referenced files to Wiro. Avoid submitting sensitive or confidential material unless that transfer is authorized. The verdict is benign with medium confidence, but the scan was partial: some local references could not be resolved, so the evidence is incomplete.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Workflow execution sends user content to Wiro without a user-facing privacy warning.

Medium
Category
Output Handling
Confidence
90% confidence
Finding

The run instructions submit user inputs and file URLs to Wiro for remote model processing, but do not instruct the agent to disclose that data transfer to the user. The credential warning elsewhere protects keys and passwords in saved workflows, but does not address the privacy implications of transmitting other sensitive user content.

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 · SKILL.md (reported line 120)May include surrounding context.

From code: the REST API

Base URL https://api.wiro.ai/v1, every endpoint POST with JSON, auth headers as in the wiro-ai skill (x-api-key, plus x-nonce and x-signature for a Signature project).

bash
# Start a run: answers at once with a run token

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 · SKILL.md (reported line 130)May include surrounding context.

{"result": true, "errors": [], "workflowtoken": "..."}

Poll until status is completed, failed, stopped or cancelled

curl -s -X POST "https://api.wiro.ai/v1/Workflow/RunDetail"
-H "Content-Type: application/json" -H "x-api-key: ${WIRO_API_KEY}"
-d '{"workflowtoken": "WORKFLOW_TOKEN"}'

text

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% 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 · SKILL.md (reported line 124)May include surrounding context.

bash
# Start a run: answers at once with a run token
curl -s -X POST "https://api.wiro.ai/v1/Workflow/Run" \
  -H "Content-Type: application/json" -H "x-api-key: ${WIRO_API_KEY}" \
  -d '{"slug": "product-shots-a1B2c", "input": {"product_photo": "https://example.com/mug.jpg"}}'
# {"result": true, "errors": [], "workflowtoken": "..."}

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 · SKILL.md (reported line 124)May include surrounding context.

bash
# Start a run: answers at once with a run token
curl -s -X POST "https://api.wiro.ai/v1/Workflow/Run" \
  -H "Content-Type: application/json" -H "x-api-key: ${WIRO_API_KEY}" \
  -d '{"slug": "product-shots-a1B2c", "input": {"product_photo": "https://example.com/mug.jpg"}}'
# {"result": true, "errors": [], "workflowtoken": "..."}