Back to skill

Security audit

高压水枪冲洗解压视频

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for WeryAI video generation, but its helper script can upload any readable local file path passed as an image, which is broader than users should accept without review.

Install only if you trust the publisher and will use public HTTPS image URLs. Do not pass local paths unless you have reviewed the script, isolated the runtime, and explicitly intend that exact file to be uploaded to WeryAI; avoid running it where it can read private workspaces, credentials, or personal documents.

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:206
Finding

Unrestricted Local File Read and External Upload Through Image Input

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}).`); } const uploade ...[truncated 3992 chars]
Remediation
View remediation
Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Findings (21)

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+. 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 21)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 22)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 28)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 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 30)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 35)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 61)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 67)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 68)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 69)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 123)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 156)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 165)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 202)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 83)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
93% confidence
Finding

The skill requires environment secrets and network access, but it does not explicitly declare a restrictive tool scope such as permissions or allowed-tools. That makes the runtime trust boundary unclear: an installer or agent may allow broader execution than intended, including reading secrets like WERYAI_API_KEY and making outbound requests without an explicit least-privilege declaration. In this skill’s context, that is more concerning because the document explicitly instructs use of Node.js, external API calls, and possible local file reads/uploads.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The implicit trigger uses a broad natural-language description in Chinese that could match ordinary user requests without clear boundaries, increasing the chance of unintended skill activation. In a media-generation skill, this can cause the agent to invoke the package when the user did not explicitly opt into this specific skill, leading to incorrect routing, unexpected external model use, or policy bypass in multilingual contexts.

Content

No source excerpt is available for this finding.

Description-Behavior Mismatch

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation explicitly allows image/images[] values that are not public HTTPS URLs to be treated as local filesystem paths, read from disk, and uploaded to a separate remote endpoint using the API key. That expands the skill from simple remote media generation into local file access and exfiltration behavior, which is dangerous if an agent can be induced to reference unintended local files; the pressure-wash video context does not require this capability and makes it harder to justify safely.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The documented read-and-upload capability is not clearly necessary for a skill whose stated purpose is generating pressure-wash reveal videos from prompts or supplied images. Unnecessary filesystem access increases the attack surface for prompt-induced data exfiltration or accidental upload of sensitive local assets, especially because the upload goes to a different service endpoint than the main video generation API.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
83% confidence
Finding

Forcing activation on a non-English prompt without documenting language handling or user opt-in can make trigger behavior unpredictable across locales and increase accidental invocation. While not directly enabling code execution, it weakens user-intent validation and may cause the skill to process requests in languages it has not clearly declared support for.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.