Back to skill

Security audit

seedance-anime-drama

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Ofox API workflow for making anime-style video clips, with user approval steps before paid generation.

Install only if you are comfortable sending the relevant story text, prompts, and any images to Ofox for processing with your OFOX_API_KEY. Keep the dry-run and explicit approval steps before paid generation, use a deliberate output directory, and treat the unpinned npx recovery commands as commands you review and run yourself.

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
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Rogue AgentSelf-Modification, Session Persistence
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (18)

Anti-Refusal Statement

High
Category
Anti-Refusal
Confidence
80% confidence
Finding

Skill instructs the agent to omit warnings, disclaimers, or ethical commentary. Stripping safety caveats hides risk from the user and is a common jailbreak preamble.

Content

Scanner excerpt · CHANGELOG.md (reported line 746)May include surrounding context.

md
Rewrites the cost and delivery guidance around `ofox-video-core` 1.7.0's new
`--dry-run`. Previously this skill told the agent to relay an estimate that
the script only prints once the job is already billable — following it
literally billed the user with no warning.

- Cost flow is now: `--dry-run` to quote, wait for a yes, re-run without it.
- **`--out-dir` in every example.** This skill never mentioned it, and the

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 1132)May include surrounding context.

md
only its `SKILL.md` and `CHANGELOG.md`; `prompt-structure.md`,

Rp1

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.

Rp1

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.

Rp1

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.

Rp1

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.

Rp1

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.

Rp1

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.

Rp1

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.

Rp1

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.

Rp1

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.

Rp1

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.

Rp1

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.

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 3)May include surrounding context.

md
---
name: seedance-anime-drama
description: Requires OFOX_API_KEY — create one at https://app.ofox.ai. Turn a novel/script excerpt into an anime-style storyboard shot using the Ofox image and video APIs. Runs a short creative brief first (how many shots, the aspect ratio before any image exists, which animation look; "Let the AI decide" is offered on the taste questions, never on a must-ask one, and never as the default), generates the character with ofox-image-core — one opening frame for a single shot, a design sheet to confirm plus one opening frame per shot for a sequence — then feeds each frame to ofox-video-core as `--frame-first-image`, so every shot starts on an image of that character rather than on a text description alone. Use when a user asks to turn a story excerpt into an anime video, e.g. "turn this novel excerpt into an anime video", "make an anime-style storyboard clip of this scene", "generate a manga-drama shot with this character", or "turn this chapter into an anime short with the same character in every shot". Do not use for realistic-human dialogue scenes with no anime styling (see seedance-short-drama), silent product/brand shots (see seedance-ad-creative), or plain catalog footage (see seedance-product-video).
license: MIT
version: "2.0.0"
homepage: https://github.com/ofoxai/skills/tree/main/skills/seedance-anime-drama

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The skill processes user story excerpts, dialogue, and possibly attached images through external Ofox image/video APIs, but the top-level description does not clearly warn the user that this content will leave the local environment. That creates a material privacy and data-handling risk because users may submit copyrighted, sensitive, or confidential text/images without informed consent.

Content

No source excerpt is available for this finding.

Unbounded Output

Medium
Category
Output Handling
Confidence
60% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · CHANGELOG.md (reported line 575)May include surrounding context.

md
RULES — quiet: one action per segment, long enough to read. No fast cutting, no time-lapse, no jump cuts.

[<segment title>, 0–<a>s] <shot size, camera position, movement>. <tag> <action A → B → C>. <the environment answers: petals lift, the light brightens>. [<Tag>: "<line>"]
<TRANSITION — name a kind on purpose; a hard cut is one of nine, and an unnamed boundary becomes one by default: HARD CUT. | Without cutting, <a sleeve / a banner / a passing body> sweeps across the lens and the camera comes out of the occlusion on <the next view>. | Without cutting, the camera pushes through <the doorway / the torii / the gap in the hedge> into <the next space>. | <an element inside the frame moves and carries the change — case 29's four shots inside one declared continuous take>. | <a speed ramp past the lens into the next beat — case 11>. | Without cutting, …>
[<segment title>, <a>–<b>s] … (each segment raises the stakes or the feeling one step)
[Ending, <x>–<T>s] <terminal pose: faces the lens | freeze | slow pull-back to a wide | arm raised>; hold one second.

Unbounded Output

Medium
Category
Output Handling
Confidence
60% confidence
Finding

Output size or generation rate is not bounded. Unbounded output enables denial-of-service through resource exhaustion, log flooding, or context-window stuffing.

Content

Scanner excerpt · SKILL.md (reported line 338)May include surrounding context.

md
RULES — quiet: one action per segment, long enough to read. No fast cutting, no time-lapse, no jump cuts.

[<segment title>, 0–<a>s] <shot size, camera position, movement>. <tag> <action A → B → C>. <the environment answers: petals lift, the light brightens>. [<Tag>: "<line>"]
<TRANSITION — name a kind on purpose; a hard cut is one of nine, and an unnamed boundary becomes one by default: HARD CUT. | Without cutting, <a sleeve / a banner / a passing body> sweeps across the lens and the camera comes out of the occlusion on <the next view>. | Without cutting, the camera pushes through <the doorway / the torii / the gap in the hedge> into <the next space>. | <an element inside the frame moves and carries the change — case 29's four shots inside one declared continuous take>. | <a speed ramp past the lens into the next beat — case 11>. | Without cutting, …>
[<segment title>, <a>–<b>s] … (each segment raises the stakes or the feeling one step)
[Ending, <x>–<T>s] <terminal pose: faces the lens | freeze | slow pull-back to a wide | arm raised>; hold one second.

External Transmission

Medium
Category
Data Exfiltration
Confidence
50% 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 · SKILL.md (reported line 1004)May include surrounding context.

md
| `minimax/hailuo-3` ("hailuo") | 768p, 8 cents/s — no 480p tier | 2k, uniquely among the three, at 13 cents/s | 4–15s — the shortest **maximum** of the three, so it's out for anything past 15s | 7, incl. 21:9 | **Accepted** the same two clips, 32 cents each (4s/768p, its minimum). Same caveat: two content classes tested, not a blanket clearance. |

Price, max resolution, duration and aspect-ratio counts are catalog facts —
`GET https://api.ofox.ai/v1/models/catalog`, no API key needed, publicly
re-checkable any time — not results from a real generation. The moderation
column is the one column here that came from a real, paid API call, and it
is directly relevant to this skill: the anime t2v prompt that