Story Video Generator

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 4:54 AM UTC
• Version: 1.0.0

Overview

This skill is a coherent video-generation workflow that creates media files in an output folder and uses FFmpeg for final assembly, with no evidence of hidden persistence, exfiltration, or destructive behavior outside its generated outputs.

Before installing, expect the skill to create and overwrite files under output/ and to use FFmpeg for local video processing. Confirm before letting it install FFmpeg, and avoid running it in a workspace where existing output/ media files must be preserved unless they are backed up or renamed.

A.I.G

Vulnerability Patterns

• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally
• Unauthorized Access and Privilege Escalation: Obtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns

• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Tool Misuse: Tool Parameter Abuse, Chaining Abuse, Unsafe Defaults
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (13)

Tool Parameter Abuse

High

• Category: Tool Misuse

Content

### 步骤3: 创建拼接列表
```bash
rm -f output/merged/filelist.txt
for i in $(seq -w 1 $segment_count); do
 echo "file 'scaled_${i}.mp4'" >> output/merged/filelist.txt
done

• Confidence: 85% confidence
• Finding: Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Vague Triggers

Medium

• Confidence: 91% confidence
• Finding: The skill description contains very broad activation phrases such as requests for generating 'video stories', 'short videos', 'image-to-video', and 'text-to-video', without clear routing boundaries or exclusion criteria. In an agentic system, this can cause the skill to trigger on common creative requests more often than intended, increasing the chance of inappropriate tool use, unexpected execution flow, or accidental handling of requests that should be served by a narrower or safer skill.

Natural-Language Policy Violations

Medium

• Confidence: 94% confidence
• Finding: This markdown file contains all operational instructions in Chinese, and there is no indication that users may choose another language or that the skill is intentionally limited to a Chinese-speaking context. Under the policy, forcing a specific language without user opt-in is a natural-language policy violation.

Natural-Language Policy Violations

Medium

• Confidence: 92% confidence
• Finding: This markdown file presents all operational instructions in a single forced language, which can violate a language/locale policy when users are not given any option to choose their preferred language. There is no indication that the skill is region-specific or that Chinese is an explicitly documented requirement.

Natural-Language Policy Violations

Medium

• Confidence: 95% confidence
• Finding: The instruction states that every `visual_desc` 'must include English word prompts,' imposing a language requirement regardless of the user's preferred language. This is a natural-language policy concern because it forces a specific language without offering choice or documenting a justified locale constraint.

Natural-Language Policy Violations

Medium

• Confidence: 89% confidence
• Finding: The entire skill instruction is written only in Chinese and does not offer any language or locale choice. Under the stated policy, forcing a specific language without user opt-in can be a natural-language policy violation unless the locale restriction is explicitly justified, which is not present here.

Missing User Warnings

Medium

• Confidence: 91% confidence
• Finding: This markdown instructs the user to delete `output/merged/filelist.txt` with `rm -f`, and elsewhere uses `ffmpeg -y` to overwrite outputs, but the document does not explicitly warn that existing generated files may be removed or overwritten. For markdown files, safety-affecting behaviors that can impact user data or existing artifacts should be disclosed clearly.

Natural-Language Policy Violations

Low

• Confidence: 75% confidence
• Finding: The document is primarily written in Chinese, but it also mandates English prompt fragments like `same subject as reference image` and style keywords such as `Ghibli style` and `Photorealistic`. This can amount to a language/locale constraint without an explicit opt-in or documented justification.

Missing User Warnings

Low

• Confidence: 82% confidence
• Finding: This markdown file defines file outputs such as `output/frames/frame_01.png` and subsequent frame files, which are user-data-affecting write operations. The instructions do not include any warning about file creation or possible overwriting of existing frame images in `output/frames`.

Natural-Language Policy Violations

Low

• Confidence: 93% confidence
• Finding: The file instructs that every `visual_desc` 'must include English word prompts', which imposes a specific language requirement on output. This is a natural-language policy concern because the skill does not offer the user a language choice or explain why English is required.

Missing User Warnings

Low

• Confidence: 89% confidence
• Finding: This markdown file explicitly directs the skill to save generated JSON to `output/story_script.json`, which is a file write affecting the user's workspace. The description provides no warning, confirmation, or disclosure that a file will be created or overwritten.

Natural-Language Policy Violations

Low

• Confidence: 95% confidence
• Finding: The file presents all operational instructions in Chinese and does not indicate that the user can choose another language or that the skill is intentionally restricted to a Chinese-speaking context. Per the policy, forcing a specific language without opt-in can be a natural-language policy violation.

Missing User Warnings

Low

• Confidence: 84% confidence
• Finding: The FFmpeg command uses `-an`, which strips audio from each scaled segment, but the markdown does not warn that audio tracks from input clips will be discarded in the intermediate files and replaced later by background music. This omission could surprise users expecting original clip audio to be preserved.

Static analysis

No suspicious patterns detected.