Back to skill

Security audit

PageClaw

Security checks for vulnerabilities and agentic risk

Overview

This skill is mostly coherent for managing a Facebook business page, but it handles a powerful Page access token in a way that could expose it through logged URLs.

Review this skill before installing. Only use a minimally scoped Facebook Page token, prefer header-based authorization instead of query-string tokens, and ensure operators understand that the agent can read customer conversations, reviews, and analytics and can post or reply after user confirmation.

Vulnerability Patterns
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
Findings (1)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:50
Finding

Facebook Page Access Token Exposed Through URL Query Strings

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly instructs the agent to read recent conversations and reviews from a Facebook Page, which can include private customer communications and sensitive business interactions, but the skill description does not clearly disclose this privacy-sensitive access. This creates a transparency and consent problem: operators or downstream users may enable the skill without realizing it ingests private message content, increasing the risk of inappropriate data access or mishandling.

Content

No source excerpt is available for this finding.