Back to skill

Security audit

读书种草

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent book-promotion video planning guide that uses disclosed web research and does not include code, persistence, credential access, or destructive behavior.

Install this if you want structured help producing book-promotion short videos. Before use, treat uploaded screenshots, unpublished pages, notes, or sales data as potentially sensitive, and ask the agent to use only public metadata or an offline workflow when needed.

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
  • 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 (2)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill description is extremely broad and overlaps with many generic content-creation requests, increasing the chance it will be invoked outside its intended scope. Misrouting is dangerous here because the skill is authorized to proactively perform web research, infer facts, and generate persuasive commercial content, which could cause unintended data exposure, low-integrity outputs, or inappropriate automation in unrelated contexts.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The skill repeatedly instructs the agent to proactively research user-provided materials and external platform content, but it does not require notice, consent, or minimization before transmitting or deriving information from uploaded content. In context, users may upload book photos, screenshots, notes, or commercially sensitive materials; automatic external lookup without clear privacy boundaries can leak personal data, purchase history, identifiers, or unpublished content to third-party services.

Content

No source excerpt is available for this finding.