Back to skill

Security audit

world-as-100-people-video-gen

Security checks for vulnerabilities and agentic risk

Overview

The skill is a disclosed WeryAI video generator, but its helper script can upload arbitrary local files passed as image inputs without technical scoping or an opt-in flag.

Install only if you are comfortable with WeryAI receiving prompts and any image files you deliberately provide. Use public HTTPS image URLs where possible; if using local files, run the skill from a limited workspace or sandbox and verify the exact path before generation. Do not pass untrusted or agent-generated image paths without checking them first.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/video_gen.js:193
Finding

Arbitrary Local File Upload Through Unvalidated Image Paths

Content
View full analysis
controller.abort(), 60_000); let res; try { res = await fetch(MODELS_BASE_URL + UPLOAD_API_PATH, { method: 'POST', headers: { Authorization: `Bearer ${apiKey}`, }, body: form, signal: controller.signal, }); } catch (err) { clearTimeout(timer); if (err.name === 'AbortError') { throw new Error(`Upload timeout: ${filePath}`); } throw err; } clearTimeout(timer); let data; try { data = await res.json(); } catch { throw new Error(`Upload failed with non-JSON response (HTTP ${res.status}).`); } const wrapped = { httpStatus: res.status, ...data }; if (!isApiSuccess(wrapped)) { const apiErr = formatApiError(wrapped); throw new Error(apiErr.errorMessage || `Upload failed (HTTP ${res.status}).`); } ...[truncated 4195 chars]
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (12)

Tp4

High
Category
MCP Tool Poisoning
Confidence
95% confidence
Finding

The description presents a narrow infographic video skill, but the content indicates broader capabilities including generic video generation, model discovery, task polling, image upload, and possible local file exfiltration to remote storage. This mismatch undermines informed consent and security review because users and operators may approve a seemingly narrow skill that can perform materially broader data handling and network behaviors.

Content

No source excerpt is available for this finding.

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:** `WERYAI_API_KEY` + Node.js 18+. **`scripts/video_gen.js`** + **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_API.md)**. **No other Cursor ski

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 20)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. **`scripts/video_gen.js`** + **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_API.md)**. **No other Cursor ski

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:** `WERYAI_API_KEY` + Node.js 18+. **`scripts/video_gen.js`** + **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_API.md)**. **No other Cursor ski

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:** `WERYAI_API_KEY` + Node.js 18+. **`scripts/video_gen.js`** + **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_API.md)**. **No other Cursor ski

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 28)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. **`scripts/video_gen.js`** + **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_API.md)**. **No other Cursor ski

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 68)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. **`scripts/video_gen.js`** + **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_API.md)**. **No other Cursor ski

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 69)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. **`scripts/video_gen.js`** + **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_API.md)**. **No other Cursor ski

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding

The skill declares access to environment secrets and network use in metadata, but it does not define an explicit tool/permission scope such as allowed-tools or permissions. That creates an authorization ambiguity where the runtime or reviewer cannot easily verify what external actions the skill is permitted to perform, increasing the risk of unintended secret access or outbound requests.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The documentation explicitly permits non-HTTPS image inputs to be treated as local filesystem paths and uploaded after being read from disk. In a skill whose business purpose is infographic video generation, this expands capability into host file access and outbound exfiltration, which is security-relevant and unnecessary unless tightly gated. The surrounding guidance even says to use local paths only after review and consent, which suggests the risk is known but not technically enforced.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The documented behavior allows arbitrary local files with accepted image extensions to be read and POSTed to an external endpoint using the API key, creating a direct local-file exfiltration path. Even if limited to image-like extensions, sensitive screenshots, exported documents renamed as images, or private generated assets could be unintentionally disclosed; in an agent setting, any file-read capability beyond the task scope is especially dangerous.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

The line states 'English only unless user requests otherwise,' which imposes a default language choice without explicit user opt-in. The policy allows language constraints when the skill offers a choice or the constraint is clearly justified, but here the default preference is enforced rather than presenting a neutral language selection.

Content

No source excerpt is available for this finding.