Security audit

Cinematic Video

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed CellCog video-generation skill with ordinary installation and API-key requirements, though users should install dependencies carefully and ensure media rights are cleared.

Before installing, use an isolated environment where practical, verify the CellCog package/source and publisher, avoid automatic upgrades when reproducibility matters, and only use brand assets, music, logos, or identifiable people when you have the necessary rights or consent.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:255
Finding: Unpinned Third-Party Dependency Installation
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (4)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 83% confidence
Finding: The skill encourages creation of brand films, product videos, and similar commercial media but does not warn about rights clearance for logos, trademarks, copyrighted music, uploaded assets, or identifiable people. In this context, users may unknowingly generate or submit infringing or unauthorized materials, creating legal, privacy, and misuse risk.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 94% confidence
Finding: The documentation instructs users to run npx skills add cellcog/skills --skill cellcog without pinning an explicit version. This can cause users to fetch and execute whatever version is current at install time, increasing supply-chain risk if the package or upstream registry entry is compromised or a breaking/malicious update is published.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 76% confidence
Finding: Natural-language policy issues include forcing a format or locale without opt-in. Here, the skill presents widescreen 16:9 as the default and recommended format, which is later reinforced as the intended way cinema should be experienced, rather than framing it as an optional default based on user needs.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 81% confidence
Finding: The statement '16:9 is your default. It's how cinema is meant to be experienced.' is a natural-language constraint that pushes one format as mandatory or normative. The policy allows such constraints only when users are given a choice or the restriction is clearly justified; neither is done in this line.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.