ClawHub
Back to skill

Security audit

Cross-Channel & Cross-Agent Skill Sharing

Security checks for vulnerabilities and agentic risk

Overview

The skill is not malicious, but it asks agents to persist capability notes, alter reusable skill instructions, and notify other sessions automatically enough that users should review it before installing.

Install only if you want agents in this workspace to maintain shared capability notes and notify related sessions after tool or package installs. Review whether automatic memory logging, reusable skill edits, and sessions_send messages are acceptable in your workspace policy, and prefer requiring explicit approval before those persistent or cross-session steps run.

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
  • Rogue AgentSelf-Modification, Session Persistence
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
Findings (3)

Tp4

High
Category
MCP Tool Poisoning
Confidence
99% confidence
Finding

The declared purpose describes a coordination/update mechanism that records and propagates newly available capabilities after installs, including documentation updates and notifications. The supplied code does none of that. It is a narrow verification utility that tests import availability of Python modules for a given interpreter. While such a check could support a larger capability-propagation workflow, on its own it has a materially different primary purpose and lacks the key declared behaviors and resources.

Content

No source excerpt is available for this finding.

Ae1

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 23)May include surrounding context.

md
- Add/adjust `SKILL.md`

Session Persistence

Medium
Category
Rogue Agent
Confidence
60% confidence
Finding

Skill establishes unauthorized persistence across sessions via cron jobs, startup scripts, or state files. Session persistence allows an attacker to maintain access beyond the current interaction.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

md
- Package versions
   - One-line usage note

3. Create or update a reusable skill when pattern is repeatable:
   - Add/adjust `SKILL.md`
   - Add scripts under `scripts/` for deterministic steps
   - Keep instructions concise and invocation-focused