Back to skill

Security audit

收纳整理解压视频

Security checks for vulnerabilities and agentic risk

Overview

This skill mostly does what it says, but its bundled video script can upload any readable local file path to WeryAI if used as an image input.

Install only if you trust WeryAI with your prompts and media, use a limited/test API key, prefer public HTTPS image URLs, and do not allow local image paths unless you have verified the exact file, size, and destination. Run in an isolated workspace if sensitive files are readable by the agent process.

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

Error
Location
scripts/video_gen.js:163
Finding

Unrestricted Local File Upload Through Image Parameters

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)) { ...[truncated 4013 chars]
Remediation
View remediation
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • 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
Findings (20)

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 29)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. When you run the CLI, **`scripts/video_gen.js`** must exist; **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 39)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. When you run the CLI, **`scripts/video_gen.js`** must exist; **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 45)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. When you run the CLI, **`scripts/video_gen.js`** must exist; **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 46)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. When you run the CLI, **`scripts/video_gen.js`** must exist; **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. When you run the CLI, **`scripts/video_gen.js`** must exist; **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 53)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. When you run the CLI, **`scripts/video_gen.js`** must exist; **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. When you run the CLI, **`scripts/video_gen.js`** must exist; **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 59)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. When you run the CLI, **`scripts/video_gen.js`** must exist; **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 85)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. When you run the CLI, **`scripts/video_gen.js`** must exist; **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 91)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. When you run the CLI, **`scripts/video_gen.js`** must exist; **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 92)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. When you run the CLI, **`scripts/video_gen.js`** must exist; **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 93)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. When you run the CLI, **`scripts/video_gen.js`** must exist; **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 140)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. When you run the CLI, **`scripts/video_gen.js`** must exist; **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 181)May include surrounding context.

md
**Dependencies:** `WERYAI_API_KEY` + Node.js 18+. When you run the CLI, **`scripts/video_gen.js`** must exist; **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 107)May include surrounding context.

md
- Do not hard-code absolute paths in this doc; run from the skill package root (next to `SKILL.md`) so `scripts/` and `resources/` paths resolve.

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill declares runtime use of environment secrets and network access but does not restrict tool scope with an explicit permissions or allowed-tools policy. In agent environments, that can let the skill be invoked with broader capabilities than intended, increasing the chance of secret exposure or unintended external requests.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The description uses broad, everyday-language SEO and invocation phrasing that could cause overbroad or accidental activation in response to casual user requests. That matters because the skill can trigger networked, paid API actions and use an API key, so ambiguous matching may lead to unintended cost, data disclosure, or execution.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The phrase 'describe the scene in one line and generate' creates an ambiguous activation condition and implies immediate execution from minimal input. In this skill, that is risky because execution can send prompts or media to external services and incur paid usage, so a vague request may be escalated into an unintended API call.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The implicit trigger test uses a broad natural-language prompt that describes organizing behavior without defining clear activation boundaries. This can cause the skill to trigger on ambiguous user requests, increasing the risk of unintended invocation, policy bypass around tool selection, or overbroad matching in multilingual contexts.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The only implicit-domain trigger example is written in Chinese, which can imply the skill expects or privileges a specific language. The file does not state that users may invoke the skill in other languages or explain a justified locale restriction.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.