Back to skill

Security audit

AI Shopping Visibility

Security checks for vulnerabilities and agentic risk

Overview

ClawScan rates this skill benign: the scanners reported no AIG issues and one low-confidence-in-context concern, while the overall evidence is incomplete because three referenced paths were not found.

The verdict is benign, but it does not mean risk-free. Consider that Skillspector could not resolve three referenced paths, leaving the evidence incomplete; install only if you are comfortable with that uncertainty.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

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 187)May include surrounding context.

md
- The user wants invented GTINs, fake or incentivised reviews, review gating, fake reference prices, or hidden text or instructions aimed at AI. Refuse and explain the platform and legal risk.
- A step would change the live feed, Merchant Center settings, product pages or checkout. Draft the change and get explicit permission for that specific change.
- Products are regulated (supplements, medical devices, weapons, alcohol, financial products) and AI answers make claims about safety or effects. Report them to the user; that's beyond a shopping fix.
- Unacceptable output: a single run reported as a rate, prices you didn't observe on the stated date, a guarantee that products will appear, or programme details stated as fact without checking current docs.

## Next step