Back to skill

Security audit

Scrapfly Agent Rules

Security checks for vulnerabilities and agentic risk

Overview

This is a disclosed Scrapfly MCP guidance skill with no bundled executable code, though users should explicitly approve persistent alerts and watch paid browser-session usage.

Use this skill only with a Scrapfly MCP server and API key you trust. Before allowing alert_create with confirm=true, review the exact metric, threshold, project, notification behavior, and expected firing rate, then give explicit approval. Monitor Cloud Browser sessions because they can keep consuming credits until closed.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill explicitly directs the agent to proceed from preview to alert_create(..., confirm=true) after showing a dry run, but it does not require fresh user confirmation immediately before committing a persistent alert. In an autonomous agent context, this can cause unintended creation of lasting monitoring rules, generating noisy alerts, external notifications, or configuration drift without clear user intent.

Content

No source excerpt is available for this finding.