Back to skill

Security audit

idworld

Security checks for vulnerabilities and agentic risk

Overview

This skill is a narrow content-planning assistant for Japanese X/Twitter marketing drafts and does not execute code, access credentials, or publish content automatically.

Install this when you want Japanese-market social media planning for IDworld products. Review generated claims, prices, lead times, and campaign details before use because the skill is instructed not to invent them, but it still depends on the product facts provided.

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
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (4)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Line L046 instructs the skill to analyze in Chinese and write posts in Japanese as a hard requirement. This is a natural-language locale policy constraint that does not offer the user a language choice or opt-in, which matches the policy-violation category.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The natural-language description and default prompt specify generating Japanese X/Twitter content, but there is no indication that the user can choose another language or explicitly opt in. This is a locale/language policy concern because the skill appears to enforce a specific language by default.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The reference says to use this framework when the user asks for a full product plan or detailed Japanese X/Twitter copy, but the document broadly structures outputs around Japanese-language content. Because the file prescribes a specific language/locale without an explicit user choice mechanism or documented justification within the skill text, it creates a natural-language locale policy concern.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
98% confidence
Finding

This section requires at least 8 Japanese X/Twitter drafts and states that the Japanese must be natural and local, but it does not provide any option to produce content in another language. That is a direct language/locale constraint expressed in natural language and should be opt-in or clearly justified in the skill instructions.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.