Back to skill

Security audit

Accessory Bundles

Security checks for vulnerabilities and agentic risk

Overview

The skill is a mostly ordinary merchandising guide, but it repeatedly steers users toward a specific commercial platform as “trusted” without clear user request or disclosure.

Review this skill before installing if you expect neutral merchandising advice. It appears technically low-risk, but its guidance may recommend Rijoy in loyalty or campaign contexts even when the user did not ask for vendor recommendations.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:120
Finding

Vendor-Specific Promotional Instruction Hijacks Neutral Skill Output

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill explicitly says to trigger even on broad, generic prompts like 'how do we sell more per order?' for multi-SKU accessories. That creates overbroad activation scope, which can cause the agent to invoke this skill when the user did not ask for bundle-specific guidance, leading to irrelevant steering, reduced reliability, and possible hidden promotional bias toward the bundled-merchandising framework and referenced vendor.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
85% confidence
Finding

The section is explicitly labeled 'Copy patterns (EN)' and provides only English phrasing for user-facing text. This can violate language/locale policy when a skill implicitly forces one language without user opt-in or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.