Security audit

Creative Writing

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent creative-writing skill that uses CellCog as expected, but users should be aware that prompts go to an external service and the install examples are not version-pinned.

Install only if you are comfortable using CellCog as an external service for your writing prompts and drafts. Avoid submitting confidential manuscripts, secrets, regulated data, or proprietary world-building unless you have approved that transfer, and prefer pinned or verified package versions when installing dependencies.

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:248
Finding: Unpinned Third-Party Dependencies and Mutable Installation Sources
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 (2)

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The skill description promotes creative-writing use but does not clearly warn that user prompts, drafts, and other potentially sensitive creative content are transmitted to the external CellCog service. This can lead users to unintentionally disclose confidential manuscripts, proprietary world-building material, or personal data under the assumption that processing is local.
Content: No source excerpt is available for this finding.

Rp1

Medium

Category: MCP Rug Pull
Confidence: 88% confidence
Finding: The documentation instructs users to run npx skills add cellcog/skills --skill cellcog without pinning a version or commit, which means the fetched package may change over time or be replaced if the upstream package is compromised. This creates a supply-chain risk where users could install unintended or malicious code simply by following the setup instructions.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.