ClawHub
Back to skill

Security audit

video-extend-edit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed video-extension workflow that uses local ffmpeg steps and the Ofox API with user approval before paid generation.

Before installing, be aware that generated jobs send a frame and prompt to Ofox and may cost money. Review or install the required ofox-video-core dependency from the same source, keep the API key scoped appropriately, and only run paid commands after the dry-run cost is shown and approved.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Rogue AgentSelf-Modification, Session Persistence
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (14)

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 85)May include surrounding context.

md
- **An ACTION verb that has no starting state in the attached frame does
  nothing, and says nothing.** The clause asked a hard case lid to close onto
  its base; in the anchor frame that case was already closed. No error, no
  warning, nothing in the returned metadata. The other half of the same ACTION
  line — a cloth drawn out of frame — landed in the same job, verified as a
  real translation rather than the push-in cropping it out. "Read the PNG

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 · SKILL.md (reported line 606)May include surrounding context.

md
- **An ACTION verb that has no starting state in the attached frame does
  nothing, and says nothing.** The clause asked a hard case lid to close onto
  its base; in the anchor frame that case was already closed. No error, no
  warning, nothing in the returned metadata. The other half of the same ACTION
  line — a cloth drawn out of frame — landed in the same job, verified as a
  real translation rather than the push-in cropping it out. "Read the PNG

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 · SKILL.md (reported line 254)May include surrounding context.

md
ffmpeg -f concat -safe 0 -i join.txt -c copy -y joined.mp4   # exit 0, no warning

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 934)May include surrounding context.

md
packages only its `SKILL.md` and `CHANGELOG.md`, so `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.

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: video-extend-edit
description: Requires OFOX_API_KEY — create one at https://app.ofox.ai, plus a video you already have. Makes an existing clip longer, or replaces its ending. Use when a user wants more of footage they already have, e.g. "extend this 5-second clip to 15", "keep going from where this one ends", "re-shoot the ending from 4 seconds on", or "add another shot onto this". A frame is pulled out of the clip at zero cost and becomes the first frame of a newly generated segment, which is then joined onto the original. Do not use to change what is inside the picture — measured, the API accepts an edit mode field and silently ignores it, so no content-editing route exists here and none returns an error either; for two stills you already have see keyframe-animation, and for a clip from nothing see the seedance-* scenarios.
license: MIT
version: "2.0.0"
homepage: https://github.com/ofoxai/skills/tree/main/skills/video-extend-edit

Sudo/Root Execution

Medium
Category
Privilege Escalation
Confidence
70% confidence
Finding

Commands invoke sudo or root privileges. Verify this elevated access is necessary and justified.

Content

Scanner excerpt · SKILL.md (reported line 153)May include surrounding context.

command -v ffmpeg >/dev/null && echo "ffmpeg ok" || echo "ffmpeg MISSING"

text

Missing → `brew install ffmpeg` (macOS), `sudo apt-get install ffmpeg`
(Debian/Ubuntu). Find that out now rather than after a segment is paid for.
The extraction commands check for it themselves and fail before doing
anything, which is the same discipline `chain` uses so a missing dependency

Static analysis

No suspicious patterns detected.