Back to skill

Security audit

Ecommerce Dropshipping Product Research

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple dropshipping product-scoring helper with no network access, credential use, persistence, or hidden execution behavior.

Installers should treat the recommendations as rough ecommerce heuristics, not financial or compliance advice. The main caveat is that broad trigger terms may make the skill activate for general product-research requests, so users should verify that they wanted dropshipping-specific scoring.

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
  • 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 (6)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README includes an example headed and written entirely in Chinese, presenting the skill output in that language, but nowhere indicates that language selection is optional or user-driven. Under the policy rule, forcing a specific language without opt-in is a natural-language policy concern unless the locale restriction is explicitly justified.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger section is broad enough that the skill could activate for loosely related ecommerce or product-evaluation requests, increasing the chance it overrides a more appropriate skill or responds outside its intended scope. In an agentic system, ambiguous activation boundaries can cause misrouting, unexpected behavior, and unsafe reliance on heuristics where the user did not explicitly request dropshipping research.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

Including a Chinese-language scenario without any user language preference or opt-in can cause the skill to produce responses in the wrong language or prioritize region-specific marketplace tactics unexpectedly. This is primarily a quality and control-boundary issue, but in an agent setting it can degrade reliability and user comprehension, especially when mixed-language outputs are undesirable or misleading.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The trigger list includes broad generic phrases such as "dropshipping," "product research," and "product idea," which can cause the skill to activate in contexts where the user did not explicitly intend to invoke it. Unintended activation can route unrelated user queries into this skill, causing prompt hijacking of workflow, misleading outputs, or accidental disclosure of context to a skill that was not meant to run.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
78% confidence
Finding

The natural-language market extraction only recognizes a fixed set of English and a few Chinese locale terms, then defaults all other inputs to 'Generic'. This embeds a locale constraint in behavior without any user opt-in or explanation, which can create inconsistent treatment across languages/regions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

The manifest sets "language": "en", which indicates a fixed language choice. There is no accompanying indication that users can opt into another language or that the English-only behavior is required for a justified region-specific purpose.

Content

No source excerpt is available for this finding.