ClawHub
Back to skill

Security audit

商品短视频广告 Product Video Ad

Security checks for vulnerabilities and agentic risk

Overview

The skill is rated suspicious because scanners found unclear disclosure about sending prompts and images to video services, and several files were only partly analyzed.

Consider the verdict’s Review status before installing. The main practical concern is that prompts and reference images may go to external video services without clear disclosure; review the providers and what data would be sent. Scanner coverage was partial, so some behavior remains unassessed.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • 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
Findings (15)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 79)May include surrounding context.

md
node scripts/video.mjs --mode storyboard --task product-video-ad \

Incomplete referenced artifact analysis

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
node scripts/video.mjs --mode storyboard --task product-video-ad \

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

The trigger “短视频” (short video) is broader than the skill's product-advertising scope.

Medium
Category
Trigger Abuse
Confidence
95% confidence
Finding

The description explicitly activates the skill when the user says “短视频,” without requiring a product-advertising intent. This can also match requests about personal videos, educational clips, or other non-advertising content, and no exclusion conditions are provided.

Content

No source excerpt is available for this finding.

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 11)May include surrounding context.

md
从卖点到成片：写分镜 → 逐镜生成 → 拼接 → 上字幕。

和 [main-image-video](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/main-image-video/skill.md) 的分工：那个是主图位的 3 秒单镜，
这个是**多镜串联的完整广告**，15–30 秒，用于投流。

---

Skill Enumeration

Medium
Category
Agent Snooping
Confidence
80% confidence
Finding

Skill enumerates or reads other installed skills. Access to other skills' SKILL.md files or the skills directory reveals prompt instructions, capabilities, and secrets that should be invisible to peer skills.

Content

Scanner excerpt · SKILL.md (reported line 30)May include surrounding context.

md
| --- | --- |
| 配音配乐 | 脚本给文案，配音配乐请用剪辑软件 |
| 精确卡点 | 生成模型的时长是档位，卡音乐点请后期调 |
| 真人口播 | 用 [ugc-testimonial](https://github.com/dlazy-ai/ecommerce-skills/blob/main/skills/ugc-testimonial/skill.md) |

---

The generation workflow lacks disclosure that reference images and prompts are submitted to the configured video-model service.

Medium
Category
Output Handling
Confidence
88% confidence
Finding

The workflow moves from storyboard approval to generation without explicitly disclosing that reference images and prompts leave the local environment. Users could consequently submit confidential product assets or identifiable model images without understanding the external processing; approving creative content is not necessarily informed approval of that transfer.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/lib/providers.mjs (reported line 134)May include surrounding context.

js
model: () => env.GEN_MODEL_OPENAI || 'gpt-image-1',
  describe(req) {
    const ep = req.images?.length ? 'images/edits' : 'images/generations'
    return `POST https://api.openai.com/v1/${ep}  model=${openai.model()} size=${mapSize(req.size)} n=${req.batch}`
  },
  async run(req) {
    const key = env.OPENAI_API_KEY

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/lib/providers.mjs (reported line 153)May include surrounding context.

js
: await readFile(p)
        fd.append('image[]', new Blob([buf], { type: mimeOf(p) }), path.basename(p))
      }
      r = await fetch('https://api.openai.com/v1/images/edits', {
        method: 'POST', headers: { authorization: `Bearer ${key}` }, body: fd,
      })
    } else {

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/lib/providers.mjs (reported line 153)May include surrounding context.

js
: await readFile(p)
        fd.append('image[]', new Blob([buf], { type: mimeOf(p) }), path.basename(p))
      }
      r = await fetch('https://api.openai.com/v1/images/edits', {
        method: 'POST', headers: { authorization: `Bearer ${key}` }, body: fd,
      })
    } else {

External Transmission

Medium
Category
Data Exfiltration
Confidence
70% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/lib/providers.mjs (reported line 157)May include surrounding context.

js
method: 'POST', headers: { authorization: `Bearer ${key}` }, body: fd,
      })
    } else {
      r = await fetch('https://api.openai.com/v1/images/generations', {
        method: 'POST',
        headers: { authorization: `Bearer ${key}`, 'content-type': 'application/json' },
        body: JSON.stringify({

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/lib/providers.mjs (reported line 157)May include surrounding context.

js
method: 'POST', headers: { authorization: `Bearer ${key}` }, body: fd,
      })
    } else {
      r = await fetch('https://api.openai.com/v1/images/generations', {
        method: 'POST',
        headers: { authorization: `Bearer ${key}`, 'content-type': 'application/json' },
        body: JSON.stringify({

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/lib/providers.mjs (reported line 261)May include surrounding context.

js
model: (req) =>
    env.GEN_MODEL_REPLICATE ||
    (req?.images?.length ? 'black-forest-labs/flux-kontext-pro' : 'black-forest-labs/flux-dev'),
  describe(req) { return `POST https://api.replicate.com/v1/models/${replicate.model(req)}/predictions` },
  async run(req) {
    const input = { prompt: req.prompt, num_outputs: req.batch }
    if (req.images?.length) input.input_image = await asDataUri(req.images[0])

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · scripts/lib/providers.mjs (reported line 266)May include surrounding context.

js
const input = { prompt: req.prompt, num_outputs: req.batch }
    if (req.images?.length) input.input_image = await asDataUri(req.images[0])
    const j = await postJson(
      `https://api.replicate.com/v1/models/${replicate.model(req)}/predictions`,
      { input },
      { authorization: `Bearer ${env.REPLICATE_API_TOKEN}`, prefer: 'wait' },
      req.timeoutMs,