ClawHub
Back to skill

Security audit

Purefeed

Security checks for vulnerabilities and agentic risk

Overview

Purefeed is a coherent API helper for a user-authenticated Twitter/X monitoring service, with disclosed account mutations that users should treat carefully.

Install only if you have a Purefeed account and are comfortable giving the skill a Purefeed API key. Ask the agent to list the target signal or folder first and require explicit confirmation before any delete, especially DELETE /signals/:id because the artifact says it is irreversible.

SkillSpector

Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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)

Context-Inappropriate Capability

Medium
Confidence
93% confidence
Finding
The skill is scoped as a Twitter/X monitoring tool, but the documentation injects unrelated Telegram publishing, approval workflow, and fact-checking UI behaviors. That scope expansion can mislead an agent into discussing or acting on capabilities outside the declared trust boundary, increasing the risk of unintended data handling or unsafe task execution paths.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The documented API includes destructive DELETE operations, including signal and folder deletion, with one endpoint explicitly marked irreversible, but there is no instruction to require user confirmation before invoking them. An agent following this skill could perform permanent destructive actions from an ambiguous or accidental user request.

Static analysis

No suspicious patterns detected.