ClawHub
Back to skill

Security audit

message-friendly

Security checks for vulnerabilities and agentic risk

Overview

This skill transparently reformats Markdown into IM-friendly plain text and does not show hidden access, persistence, code execution, or data exfiltration behavior.

Install this if you want Markdown responses automatically converted for IM sharing. Review the auto-trigger behavior first, because it can remove Markdown formatting and may summarize very long messages before you send them.

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
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The manifest is configured to auto-trigger with broad channel matching and simple response content heuristics, causing the skill to activate on many ordinary markdown-like messages. This can unexpectedly intercept or rewrite outputs across IM contexts, increasing the attack surface for unintended behavior and making downstream message handling less predictable.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.