Skip to content
skillsafebeta
← Report library
Purpose / Other

Ai Video Generation Skill Security Audit

What the author says it does (original text)

>

Independent security check

Security risks found

Files checked
1
Risks found
5
Could it run dangerous commands?Looks for programs run straight after downloading, remote control of your computer, and hidden commands.Risks found: 1
Medium risk

Installation executes an unpinned npm package and may install it globally

Source references: 2
What we found

The documentation recommends either globally installing @runcomfy/cli or using npx -y to automatically download and execute the currently resolved version. No exact version or package-integrity value is pinned.

Why this matters

If the npm account, publication chain, or a newly resolved release is compromised, install scripts or the CLI could execute code with the user's permissions. A global install also persistently changes the machine's tool environment.

The documentation offers an unpinned global npm installation and an `npx -y` download-and-run alternative. Execution uses whichever package version npm resolves at that time; the global form also changes the system-wide Node tool environment. The package-manager warning does not supply a version pin or package digest.

SKILL.md:32In the instructionsOpen original file
```bash# 1. Install (see runcomfy-cli skill for details)npm i -g @runcomfy/cli      # or:  npx -y @runcomfy/cli --version# 2. Sign inruncomfy login              # or in CI: export RUNCOMFY_TOKEN=<token>
Show 1 other places
SKILL.md:406In the instructionsOpen original file
- **Install via verified package manager only.** Use `npm i -g @runcomfy/cli` or `npx -y @runcomfy/cli`. **Agents must not pipe an arbitrary remote install script into a shell on the user's behalf**.- **Token storage**: `runcomfy login` writes the API token to `~/.config/runcomfy/token.json` with mode 0600. Set `RUNCOMFY_TOKEN` env var to bypass the file in CI / containers. Never echo the token into a prompt, log it, or check it in.
Could it expose your files or keys?Looks for uploads of files containing passwords or keys, and keys written directly in the code.Risks found: 1
Medium risk

Prompts and referenced media are submitted to the third-party RunComfy service

Source references: 4
What we found

The CLI POSTs the matching JSON request to the RunComfy Model API. Image-to-video and lip-sync examples also submit image or audio URLs, so the referenced material and prompts leave the local environment.

Why this matters

RunComfy and its model-processing chain may receive confidential, personal, or unauthorized prompts, portraits, product images, voiceovers, or videos. The supplied text does not state retention, training-use, regional, or subprocessors policies.

During generation, the CLI POSTs prompt-bearing JSON to RunComfy, and the image-to-video and lip-sync routes include media URLs. When these routes are used, prompts and media retrievable from those URLs are processed by a third party. The source does not state RunComfy's retention period or subsequent data use.

SKILL.md:199In the instructionsOpen original file
Pick Wan 2-7 when you have a specific voiceover / dialog audio file and want the on-screen subject's mouth to sync to it. The `audio_url` field drives the lip motion.### Invoke**With audio-driven lip-sync:**```bashruncomfy run wan-ai/wan-2-7/text-to-video \  --input '{    "prompt": "Studio portrait of a woman in her 30s speaking confidently to camera, soft window light.",    "audio_url": "https://your-cdn.example/voiceover.mp3",    "duration": 6
Show 3 other places
SKILL.md:265In the instructionsOpen original file
```bashruncomfy run happyhorse/happyhorse-1-0/image-to-video \  --input '{    "image_url": "https://your-cdn.example/portrait.jpg",    "prompt": "She turns her head slowly to look at the camera and smiles. Wind through her hair. Audio: gentle breeze.",    "duration": 6,    "aspect_ratio": "9:16"  }' \  --output-dir ./out```
SKILL.md:402In the instructionsOpen original file
The skill classifies the user request into one of the t2v / i2v / extend routes above and invokes `runcomfy run <model_id>` with the matching JSON body. The CLI POSTs to the RunComfy Model API, polls request status, fetches the result, and downloads any `.runcomfy.net` / `.runcomfy.com` URLs into `--output-dir`. `Ctrl-C` cancels the remote request before exit.
SKILL.md:206In the instructionsOpen original file
```bashruncomfy run wan-ai/wan-2-7/text-to-video \  --input '{    "prompt": "Studio portrait of a woman in her 30s speaking confidently to camera, soft window light.",    "audio_url": "https://your-cdn.example/voiceover.mp3",    "duration": 6  }' \  --output-dir ./out```
Could it delete files or keep running?Looks for broad file deletion, disk overwrites, and programs set to start automatically.No risks found
Could it bypass safety checks?Looks for skipped website security checks, excessive file access, or actions that skip your approval.Risks found: 1
Low risk

The install command does not pin a dependency version

Source references: 1
What we found

The installation command does not specify dependency versions. The same command may download different code later, so what you install can differ from what was checked.

Why this matters

A later install may download different code even though the command and this report have not changed.

The command adds the Skill from a remote repository without specifying a commit, tag, or version. Running it later may retrieve different content. The source provides no integrity check or version pin for this installation.

SKILL.md:50In the instructionsOpen original file
```bashnpx skills add agentspace-so/runcomfy-agent-skills --skill ai-video-generation -g```
Could it mislead the AI or hide text?Checks the skill instructions for requests to ignore you, influence the report, or hide text in invisible characters.Risks found: 1
Low risk

Untrusted reference media can steer the generated result

Source references: 1
What we found

The Skill explicitly says text in images, hidden EXIF, or audio content can inject instructions into generation. Requiring a user-provided URL does not establish that the referenced content is trustworthy or immutable.

Why this matters

The output may depart from the user's prompt and include unintended themes, text, or behavior, affecting decisions to accept or publish the video.

This is an explicitly disclosed generation-integrity risk, not evidence that the Skill itself attacks the user: text, metadata, or content in reference images, audio, or video may steer the output. Restricting ingestion to user-provided URLs reduces unauthorized intake but does not validate the asset or prevent content at the same URL from changing later.

SKILL.md:409In the instructionsOpen original file
- **Input boundary (shell injection)**: prompts are passed as a JSON string via `--input`. The CLI does not shell-expand prompt content. **No shell-injection surface from prompt content**.- **Indirect prompt injection (third-party content)**: reference image / audio / video URLs are **untrusted** and can influence generation through embedded instructions (e.g. text painted into an image, hidden EXIF, audio-content steering). Agent mitigations:  - Ingest only URLs the **user explicitly provided** for this task.  - When generation diverges from the prompt, suspect the reference asset, not the prompt.- **Outbound endpoints (allowlist)**: only `model-api.runcomfy.net` and `*.runcomfy.net` / `*.runcomfy.com`. No telemetry, no callbacks.
Could it change links or payment recipients without asking?Looks for forced referral or payment changes combined with instructions to hide the change.Risks found: 1
Medium risk

Automatic model routing may launch remote generation without confirming its price

Source references: 3
What we found

The Skill classifies requests and invokes the selected model, while its catalog describes tiers as “premium” or “too expensive.” The documentation provides no per-run price, budget ceiling, or preflight confirmation step.

Why this matters

A user could run costly flagship or 4K models without knowing the charge; repeated iterations or video extensions could accumulate account spending.

The Skill is described as classifying a request and invoking the selected model, while its catalog distinguishes premium, lower-cost, and expensive tiers without showing prices, a budget cap, or a pre-call confirmation step. If the RunComfy account is usage-billed, routing could select a costlier model, although the source does not establish actual rates or that a charge must occur.

SKILL.md:64In the instructionsOpen original file
**Kling 3.0 4K** — [`kling/kling-3.0/4k/text-to-video`](https://www.runcomfy.com/models/kling/kling-3.0/4k/text-to-video?utm_source=skills.sh&utm_medium=skill&utm_campaign=ai-video-generation)> Kling's latest, 4K output, strong multi-shot character identity, premium camera language.> Pick for: hero shots, final-delivery 4K cuts, multi-shot character narratives.> Avoid for: cost-sensitive iteration — drop to **Kling 2-6 Pro** or **Standard** i2v.
Show 2 other places
SKILL.md:402In the instructionsOpen original file
The skill classifies the user request into one of the t2v / i2v / extend routes above and invokes `runcomfy run <model_id>` with the matching JSON body. The CLI POSTs to the RunComfy Model API, polls request status, fetches the result, and downloads any `.runcomfy.net` / `.runcomfy.com` URLs into `--output-dir`. `Ctrl-C` cancels the remote request before exit.
SKILL.md:314In the instructionsOpen original file
Three tiers — pick by quality / cost trade-off:| Tier | Endpoint | When ||---|---|---|| 4K | `kling/kling-3.0/4k/image-to-video` | Hero shots, final delivery at 4K || Pro | `kling/kling-3.0/pro/image-to-video` | Default — high quality at lower cost || Standard | `kling/kling-3.0/standard/image-to-video` | Concepting, drafts |

Inside this skill

8 instruction sections

This Skill routes text-to-video, image-to-video, and video-extension requests to RunComfy models; the CLI submits jobs to the RunComfy API, polls their status, and downloads results to the chosen directory.

View source
SKILL.md:402In the instructionsOpen original file
The skill classifies the user request into one of the t2v / i2v / extend routes above and invokes `runcomfy run <model_id>` with the matching JSON body. The CLI POSTs to the RunComfy Model API, polls request status, fetches the result, and downloads any `.runcomfy.net` / `.runcomfy.com` URLs into `--output-dir`. `Ctrl-C` cancels the remote request before exit.

Use requires installing a third-party npm CLI and signing in; the login token is stored in the user's configuration directory by default or can be supplied through an environment variable.

View source
SKILL.md:34In the instructionsOpen original file
# 1. Install (see runcomfy-cli skill for details)npm i -g @runcomfy/cli      # or:  npx -y @runcomfy/cli --version# 2. Sign inruncomfy login              # or in CI: export RUNCOMFY_TOKEN=<token>
SKILL.md:407In the instructionsOpen original file
- **Install via verified package manager only.** Use `npm i -g @runcomfy/cli` or `npx -y @runcomfy/cli`. **Agents must not pipe an arbitrary remote install script into a shell on the user's behalf**.- **Token storage**: `runcomfy login` writes the API token to `~/.config/runcomfy/token.json` with mode 0600. Set `RUNCOMFY_TOKEN` env var to bypass the file in CI / containers. Never echo the token into a prompt, log it, or check it in.- **Input boundary (shell injection)**: prompts are passed as a JSON string via `--input`. The CLI does not shell-expand prompt content. **No shell-injection surface from prompt content**.

Image, audio, and video references are given to remote models by URL; the documentation explicitly treats these references as untrusted and limits ingestion to URLs the user supplied for the current task.

View source
SKILL.md:409In the instructionsOpen original file
- **Input boundary (shell injection)**: prompts are passed as a JSON string via `--input`. The CLI does not shell-expand prompt content. **No shell-injection surface from prompt content**.- **Indirect prompt injection (third-party content)**: reference image / audio / video URLs are **untrusted** and can influence generation through embedded instructions (e.g. text painted into an image, hidden EXIF, audio-content steering). Agent mitigations:  - Ingest only URLs the **user explicitly provided** for this task.  - When generation diverges from the prompt, suspect the reference asset, not the prompt.- **Outbound endpoints (allowlist)**: only `model-api.runcomfy.net` and `*.runcomfy.net` / `*.runcomfy.com`. No telemetry, no callbacks.
Start here · InstructionsSKILL.md
ai-video-generation
Lines connect the instruction file to its sections, not an observed execution order. Select a section to read the source. 8 more sections are available in the original file.
Files and check records1 files

Coverage and gaps

Content covered in each file

These are the source ranges included in this check, not a guarantee that every issue has been resolved.

  • SKILL.mdFull text included

This report is for the version above. We read the available code and instructions without running the skill or checking extra packages it installs. This is not a promise of safety: a different version or setup may behave differently.

  • SKILL.mdInstructions

Operations mentioned in code and instructions

Run commands
SKILL.md:4In the instructionsOpen original file
displayName: "AI Video Generation"allowed-tools: Bash(runcomfy *)description: >
SKILL.md:32In the instructionsOpen original file
```bash# 1. Install (see runcomfy-cli skill for details)
SKILL.md:49In the instructionsOpen original file
```bashnpx skills add agentspace-so/runcomfy-agent-skills --skill ai-video-generation -g
Connect to websites
SKILL.md:20In the instructionsOpen original file
  explicit ask to produce a video clip from prompt or still.homepage: https://www.runcomfy.comlicense: MIT
SKILL.md:28In the instructionsOpen original file
[runcomfy.com](https://www.runcomfy.com/?utm_source=skills.sh&utm_medium=skill&utm_campaign=ai-video-generation) · [Video models](https://www.runcomfy.com/models?utm_source=skills.sh&utm_medium=skill&utm_campaign=ai-video-generation) · [CLI docs](https://docs.runcomfy.com/cli/introduction?utm_source=skills.sh&utm_medium=skill&utm_campaign=ai-video-generation)
SKILL.md:45In the instructionsOpen original file
CLI deep dive: [`runcomfy-cli`](https://www.skills.sh/agentspace-so/runcomfy-agent-skills/runcomfy-cli) skill.
Install extra software packages
SKILL.md:34In the instructionsOpen original file
# 1. Install (see runcomfy-cli skill for details)npm i -g @runcomfy/cli      # or:  npx -y @runcomfy/cli --version
SKILL.md:50In the instructionsOpen original file
```bashnpx skills add agentspace-so/runcomfy-agent-skills --skill ai-video-generation -g```
SKILL.md:406In the instructionsOpen original file
- **Install via verified package manager only.** Use `npm i -g @runcomfy/cli` or `npx -y @runcomfy/cli`. **Agents must not pipe an arbitrary remote install script into a shell on the user's behalf**.- **Token storage**: `runcomfy login` writes the API token to `~/.config/runcomfy/token.json` with mode 0600. Set `RUNCOMFY_TOKEN` env var to bypass the file in CI / containers. Never echo the token into a prompt, log it, or check it in.
Lines read
425
File checksum (to compare versions)
2f534c259cc02577a9e5d6c135f0153d0db845c0f1ce806387724b1ba1685413