Back to skill

Security audit

Comments Monitor Reply

Security checks for vulnerabilities and agentic risk

Overview

The skill describes a legitimate social-media comment monitoring tool, but it asks users to install unreviewed mutable code and handle account cookies/tokens for automated public replies.

Review bucket: install only if you trust the publisher and the referenced repository at the exact version you will use. Prefer a pinned release or reviewed commit with a lockfile, avoid running npm install as an administrator, use least-privileged platform tokens instead of main-account cookies, and enable human review before automatic replies affect public accounts.

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs
Findings (1)

T03 · Remote Payload Retrieval and Execution

Warning
Location
SKILL.md:136
Finding

Unpinned Remote Code and Dependency Retrieval During Manual Installation

Content
View full analysis
=18.0.0", "axios>=1.6.0", "cheerio>=1.0.0-rc.12", "crypto-js>=4.1.1"] ``` These constraints do not identify the exact dependency artifacts reviewed or expected at installation time. ### Attack Path 1. An attacker compromises the referenced GitHub repository, a maintainer account, or an npm dependency used by the remote project. 2. The attacker adds a malicious npm lifecycle script, modifies application code, or publishes a compromised dependency version that satisfies the open-ended version constraints. 3. A ...[truncated 1494 chars]
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)

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

This markdown file contains user-facing instructions, descriptions, and command guidance entirely in Chinese. Under the policy rule, forcing a specific language without user opt-in or a documented region-specific justification is a natural-language policy violation.

Content

No source excerpt is available for this finding.