ClawHub
Back to skill

Security audit

posterly

Security checks for vulnerabilities and agentic risk

Overview

This skill is a focused Posterly integration that uses an API key to manage social posts and requires user confirmation before publishing or other writes.

Install only if you trust Posterly with the connected social accounts and understand that approved actions can publish, delete, moderate, or affect billing/API settings. Keep the API key protected and verify the exact account, content, and schedule before approving any write.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

MCP Config Access

High
Category
Agent Snooping
Confidence
90% confidence
Finding

Skill accesses MCP server configuration files (mcp.json). MCP configs contain server URLs, authentication tokens, and tool definitions — reading them allows the skill to discover and potentially abuse other tool integrations.

Content

Scanner excerpt · SKILL.md (reported line 40)May include surrounding context.

md
Do not invent a second product surface, UI, Autopilot, or a live Claude Connectors listing. If MCP tools are missing, point the user at the MCP docs rather than pasting a long REST map.

Local stdio is optional: `npx -y posterly-mcp-server@0.50.4` with `POSTERLY_API_KEY` in the environment. Claude Code plugins that ship this package can load MCP from `.mcp.json` using plugin `userConfig.api_key`.

## Auth

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 52)May include surrounding context.

md
If the key is missing, send the user to https://www.poster.ly/mcp or https://www.poster.ly/agents/signup. Do not collect card numbers, posterly passwords, or social passwords. Do not invent a signup flow.

Never start signup if `whoami` already works. Never ask the user to paste a key they already have.

## Safe publish loop

Static analysis

No suspicious patterns detected.