Security audit

Video Generation

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward CellCog video-generation helper, with ordinary external-service and package-install risks users should understand before use.

Before installing, confirm you trust CellCog and the package source, avoid running installation with elevated privileges, and do not submit confidential, regulated, customer, or secret material unless your organization approves CellCog's data handling.

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:198
Finding: Unpinned Third-Party Dependencies and Mutable Installation Sources
Content: View full analysis
Remediation: View remediation
" ``` 3. Publish and verify cryptographic hashes, using pip hash-checking mode where practical: ```bash python3 -m pip install --require-hashes -r requirements.txt ``` 4. Pin repository-based installations to an immutable commit digest or signed release rather than a mutable branch or package identifier. 5. Provide a lockfile or fully resolved dependency manifest covering transitive dependencies. 6. Document the authoritative registry and publisher identity so users can detect dependency-confusion or namespace-spoofing attempts. 7. Remove automatic upgrade behavior from standard setup instructions. Review new releases before updating the pinned version. 8. Recommend installation inside an isolated virtual environment or container and explicitly discourage elevated installation. 9. Validate package signatures or release attestations when supported, and incorporate dependency scanning into the release process. ]]>

SkillSpector

Vulnerability Patterns

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

Findings (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill encourages users to submit prompts, scripts, and potentially sensitive business content to CellCog, but the description and usage section do not clearly warn that this data will be transmitted to an external third-party video-generation service. This can lead to unintended disclosure of confidential prompts, proprietary scripts, customer data, or other sensitive media instructions.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 92% confidence
Finding: The skill instructs users to run npx skills add cellcog/skills --skill cellcog without pinning a specific package or version. This creates a supply-chain risk because users may fetch whatever version is current at execution time, including a compromised release or typosquatted dependency chain.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.