ClawHub
Back to skill

Security audit

crosspost

Security checks for vulnerabilities and agentic risk

Overview

The skill does what it says: helps publish or schedule user-approved posts through PostWire, with clear confirmation before posting.

Before installing, confirm you trust PostWire with the social accounts you connect, review the remote setup instructions before adding the MCP server, and check each caption/network/time carefully before approving a post.

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
94% confidence
Finding

The manifest description contains broad trigger wording such as "post this everywhere" and similar natural-language phrases that are likely to appear in ordinary conversation. In agents that auto-discover or auto-invoke skills based on description matching, this can cause unintended activation of a capability that performs real external side effects: publishing content to social networks.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.