ClawHub
Back to skill

Security audit

Instagram Reels

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently uses CellCog to generate social-media content, with expected data-sharing, usage-cost, and software-installation considerations.

Use prompts and materials you are authorized to share with CellCog, and account for potentially substantial generation costs. Review the separately installed CellCog SDK and base skill, and prefer reviewed, pinned versions where supported. This review covered the complete supplied skill document, not external dependency code or service-side behavior.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

The usage workflow sends user prompts to CellCog without a privacy warning.

Medium
Category
Output Handling
Confidence
94% confidence
Finding

The usage examples instruct the agent to submit the user's task prompt to CellCog through client.create_chat. Although the skill identifies CellCog as its provider and warns about costs and output quality, it does not warn that submitted prompts, potentially including private brand or campaign information, leave the user's environment for third-party processing.

Content

No source excerpt is available for this finding.

MCP server referenced without pinned version: 'npx skills'.

Medium
Category
MCP Rug Pull
Confidence
88% confidence
Finding

The installation command invokes an unpinned skills package through npx, allowing newly fetched package code to execute with the invoking user's privileges. A compromised release could access local files or credentials; this is a supply-chain exposure, although the static finding incorrectly describes the installer as an MCP server and there is no evidence of malicious package behavior.

Content

No source excerpt is available for this finding.