Back to skill

Security audit

WooCommerce Spraay Batch Payouts

Security checks for vulnerabilities and agentic risk

Overview

The skill prepares payout batches with merchant approval for recipient changes and merchant-controlled wallet signing.

Use a dedicated store account with minimum permissions and evaluate the required plugin separately. Confirm recipient changes and review payout addresses, amounts, and fees before signing. Deleted-recipient recovery details are retained in the conversation.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (4)

Description-Behavior Mismatch

High
Category
MCP Tool Poisoning
Confidence
87% confidence
Finding

Reading recipient information is a reasonable supporting step for payout preparation. However, the chunk also provides recipient lifecycle management, including persistent changes and deletion, which is not disclosed by the description's commission-reading and batch-preparation scope. Merchant-approval requirements constrain these operations but do not make the additional capabilities declared. The chunk contains API examples rather than evidence that any requests have been executed.

Content

No source excerpt is available for this finding.

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · skill.md (reported line 125)May include surrounding context.

Delete a recipient (REQUIRES merchant approval first — show what will be deleted)

Always GET the recipient first to retain details for recovery

DELETE /wp-json/spraay/v1/recipients/{id}

text

### WooCommerce Data

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · skill.md (reported line 100)May include surrounding context.

⚠ Approval required: Agents MUST confirm with the merchant before creating, updating, or deleting recipients. See "User Control & Approval Requirements" above.

bash
# List all recipients (read-only, no approval needed)
GET /wp-json/spraay/v1/recipients

# Get a single recipient (read-only, no approval needed)

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · skill.md (reported line 103)May include surrounding context.

md
# List all recipients (read-only, no approval needed)
GET /wp-json/spraay/v1/recipients

# Get a single recipient (read-only, no approval needed)
GET /wp-json/spraay/v1/recipients/{id}

# Create a recipient (REQUIRES merchant approval first)