Back to skill

Security audit

nation-resilience-hook-video-gen

Security checks for vulnerabilities and agentic risk

Overview

The skill is mostly coherent for WeryAI video generation, but its helper script can read arbitrary local image paths and upload them externally without a technical opt-in or path limit.

Review this skill before installing if the agent can receive untrusted image parameters. Use public HTTPS image URLs only, avoid passing local paths or file:// URLs, and run it in a restricted workspace with a limited WERYAI_API_KEY if you proceed.

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:133
Finding

Unrestricted Local File Read and External Upload Through Image Parameters

Content
View full analysis
{ if (typeof value === 'string' && value.trim()) candidates.push(value.trim()); }; const maybePushMany = (value) => { if (Array.isArray(value)) { for (const item of value) maybePush(item); } }; maybePush(data.url); maybePush(data.file_url); maybePush(data.fileUrl); maybePush(data.https_url); maybePush(data.httpsUrl); maybePush(data.public_url); maybePush(data.publicUrl); maybePush(data.object_url); maybePush(data.objectUrl); maybePush(data.origin_url); maybePush(data.originUrl); maybePushMany(data.object_url_list); maybePushMany(data.objectUrlList); if (data.file && typeof data.file === 'object') { candidates.push(...collectPossibleUploadUrls(data.file)); } if (data.data && typeof data.data === 'object') { candidates.push(...collectPossibleUploadUrls(data.data)); } if (Array.isArray(data.files)) { for (const item of data.files) { candidates.push(...collectPossibleUploadUrls(item)); } } if (Array.isArray(data.list)) { for (const item of data.list) { candidates.push(...collectPossibleUploadUrls(item)); } } return candidates; } function extractUploadedFileUrl(res) { const urls = collectPossibleUploadUrls(res ...[truncated 5571 chars]
Remediation
View remediation
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • 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 (22)

Tp4

High
Category
MCP Tool Poisoning
Confidence
98% confidence
Finding

The skill description materially understates actual behavior: it can perform generic remote video generation, poll task status, query model registries, and potentially read/upload local files to external storage. This mismatch is dangerous because users and policy systems may authorize the skill for a narrow creative task while it actually has broader data-handling and network capabilities, including possible exfiltration of local content.

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)** under **`resources/`**

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)** under **`resources/`**

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+. **`scripts/video_gen.js`** + **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_API.md)** under **`resources/`**

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+. **`scripts/video_gen.js`** + **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_API.md)** under **`resources/`**

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)** under **`resources/`**

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+. **`scripts/video_gen.js`** + **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_API.md)** under **`resources/`**

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+. **`scripts/video_gen.js`** + **[`WERYAI_VIDEO_API.md`](resources/WERYAI_VIDEO_API.md)** under **`resources/`**

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 34)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)** under **`resources/`**

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)** under **`resources/`**

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 74)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)** under **`resources/`**

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 75)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)** under **`resources/`**

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 88)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)** under **`resources/`**

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 104)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)** under **`resources/`**

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
89% confidence
Finding

The skill declares network and environment variable use but does not define an explicit tool/permission scope. In practice, that means the agent may invoke external APIs and access secrets without a narrowly declared boundary, reducing auditability and increasing the chance of unintended secret exposure or unauthorized outbound actions.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill description states that English subtitles are burned in by default, derived from the user's topic unless they provide a final script. This imposes a language choice as the default behavior rather than offering a neutral language selection or explicit opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The workflow says to build a full English production prompt and marks this expansion as mandatory. That is a natural-language policy concern because it forces a specific language without first obtaining the user's preference.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The trigger prompt explicitly specifies "English subtitles with exact timing," which imposes a language requirement in natural language. Because the file does not indicate user opt-in, language choice, or a documented region-specific justification, this appears to violate the language/locale policy criteria.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

This test case requires "on-screen English text," which is a natural-language instruction forcing a specific language. The file provides no opt-in mechanism or stated justification for limiting output text to English, so it falls under the policy violation category.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The rubric states that SKILL.md must require "timed burned-in English subtitles," making English a mandatory output language at the policy level. Since no alternative language support, user choice, or justification is given, this is a clear locale-policy issue.

Content

No source excerpt is available for this finding.

Intent-Code Divergence

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The documentation presents public HTTPS image URLs as mandatory for image-to-video use, but later documents a fallback path where non-HTTPS inputs are treated as local files, read from disk, and uploaded to a remote service. That mismatch can cause downstream agents or operators to believe they are only handling remote URLs when they may actually grant the script permission to access local files and exfiltrate them to WeryAI.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The documented local-image workflow expands the skill from simple media generation into reading arbitrary local files and transmitting them to an external API. In an agent setting, that creates a data-exfiltration risk if a prompt, wrapper, or user misunderstanding causes sensitive local files to be passed as image inputs under the guise of normal video generation.

Content

No source excerpt is available for this finding.