ClawHub
Back to skill

Security audit

purrplan

Security checks across malware telemetry and agentic risk

Overview

This skill coherently connects an agent to PurrPlan for social scheduling, inbox replies, and analytics, with the main risks being normal credential and publishing risks that users should handle carefully.

Install this only if you want an agent connected to your PurrPlan account. Use the narrowest token scopes that fit your use case, store the token securely, rotate it if exposed, and be especially careful with write and inbox-reply permissions because they can post or send messages from connected social accounts. Prefer native HTTP MCP support or a pinned/vetted mcp-remote version instead of running an unpinned npx command.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
88% confidence
Finding
The description uses broad trigger phrases such as scheduling posts, replying to comments/DMs, and checking social performance, which can cause the skill to activate for a wide range of ordinary social-media requests. In an agent environment, over-broad activation increases the chance that a user is routed into a high-privilege remote MCP integration unnecessarily, expanding exposure to account actions and sensitive analytics.

Missing User Warnings

Medium
Confidence
96% confidence
Finding
The setup section tells the user to create and place a bearer token into MCP configuration headers but does not explicitly warn that the token is a sensitive credential granting direct access to social publishing, inbox reply, media, AI, and analytics capabilities. In practice, users may paste or store the token insecurely, and because the scopes can include write and reply permissions, leakage could enable account takeover-like misuse across connected social networks.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding
The skill instructs users to run `npx mcp-remote` without pinning an exact version, which creates a supply-chain risk: a later compromised or malicious package version could be fetched and executed automatically. Because this skill is specifically about connecting a privileged remote MCP server with bearer-token authentication, compromise of the bridge process could expose tokens or manipulate social-account actions.

VirusTotal

63/63 vendors flagged this skill as clean.

View on VirusTotal

Static analysis

No suspicious patterns detected.