ClawHub
Back to skill

Security audit

Presentation Slides

Security checks for vulnerabilities and agentic risk

Overview

The skill coherently uses CellCog to generate presentations, with routine privacy and dependency-installation considerations.

Presentation prompts and included business information are sent to CellCog, so submit only material you are authorized to share. Review the separate CellCog dependency and prefer reviewed, pinned installation versions. Scanner coverage was complete for the sole Markdown artifact; dependency execution and service retention remain outside this review.

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 workflow sends presentation content to CellCog without warning users that their data is transmitted to a third-party service.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The usage workflow submits the user's task prompt to CellCog through create_chat. The skill encourages supplying actual metrics, quotes, and facts (L231), including potentially confidential business content, but never explicitly discloses the external data transfer or warns against submitting sensitive information.

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 npm package through npx, allowing remotely supplied code to execute with the user's privileges. Although this is an installer rather than an MCP server, the supply-chain concern is valid: a compromised future package release could access local files or credentials. Exposure is conditional on following the optional setup instructions.

Content

No source excerpt is available for this finding.