Back to skill

Security audit

Carpet Wash Video

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed WeryAI video-generation helper that sends confirmed prompts and optional image URLs to WeryAI using the user's API key.

Install only if you intend to use WeryAI for paid video generation. Set WERYAI_API_KEY only in an environment you trust, review any WERYAI_BASE_URL or WERYAI_MODELS_BASE_URL overrides before running, and expect prompts plus optional HTTPS image URLs to be sent to the configured WeryAI endpoint after confirmation.

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
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (9)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 16)May include surrounding context.

md
**Dependencies:** `scripts/video_gen.js` + `WERYAI_API_KEY` + Node.js 18+.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 26)May include surrounding context.

md
**Dependencies:** `scripts/video_gen.js` + `WERYAI_API_KEY` + Node.js 18+.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 27)May include surrounding context.

md
**Dependencies:** `scripts/video_gen.js` + `WERYAI_API_KEY` + Node.js 18+.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 32)May include surrounding context.

md
**Dependencies:** `scripts/video_gen.js` + `WERYAI_API_KEY` + Node.js 18+.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
92% confidence
Finding

The skill requires environment secrets and network access but does not declare an explicit tool scope such as permissions or allowed-tools. That creates an authorization gap where a host may permit broader execution than users expect, increasing the chance that prompts, image URLs, or the WERYAI_API_KEY are exposed through undeclared capability use.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description uses broad trigger phrases like general cleaning and satisfying-video language, which can cause the skill to be invoked when a user did not clearly intend to run a networked, API-key-backed tool. In this context, accidental invocation matters because the skill can send user prompts and optional image URLs to an external service and consume paid resources.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The implicit trigger uses a broad natural-language request about a dirty carpet being pressure-washed into a clean boundary line, which is highly likely to match ordinary user conversation without an explicit skill invocation. This can cause unintended activation of the skill, leading the agent to route requests to this capability when the user may only be describing content or brainstorming ideas.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This code file includes its primary user-facing documentation and usage guidance in Chinese, which imposes a specific language on users without any opt-in or alternative locale. The policy explicitly flags language or locale constraints when the skill does not offer user choice or clearly justify the restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
72% confidence
Finding

The file defines a Chinese prompt as a positive trigger case, but does not explain whether multilingual triggering is intentional, optional, or limited by user preference. This can create an implicit language-policy behavior without documenting language choice or opt-in.

Content

No source excerpt is available for this finding.