Back to skill

Security audit

Textbook Authoring

Security checks for vulnerabilities and agentic risk

Overview

This is a Markdown-only textbook-writing skill with disclosed review steps and no evidence of hidden code, persistence, credential access, or data exfiltration.

Before installing, expect a Chinese-first textbook authoring workflow that may write draft files and invoke multiple review subagents. Specify your desired language, chapter scope, and whether you want the full review loop if time or token cost matters.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
94% confidence
Finding

The README says the skill can be triggered by broadly phrased natural-language requests like 'describe the chapter you want to write,' which risks unintended activation during ordinary conversation. Over-broad triggers can cause the agent to enter this skill when the user did not explicitly request textbook-authoring behavior, leading to scope confusion, unwanted prompt steering, or accidental use of the skill’s internal workflow.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
88% confidence
Finding

The skill states that output will be in Chinese by default unless the user specifies another language, which can override user expectations without explicit opt-in. This is primarily a usability and policy-risk issue: it may cause unintended language switching, reduce accessibility for some users, and create confusion in mixed-language environments.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
90% confidence
Finding

This markdown file presents all user-facing instructions exclusively in Chinese, and it does not offer an opt-in language choice or explain that the skill is intentionally limited to Chinese-speaking users. Under the policy, forcing a specific language without user opt-in can be a natural-language policy violation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
91% confidence
Finding

SQP-3 applies to all file types and includes language or locale policy violations. This document presents all instructions and examples only in Chinese, with no visible opt-in, language selection, or justification that the skill is intentionally region-specific.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
96% confidence
Finding

This markdown file contains user-facing instructional content exclusively in Chinese, and nowhere indicates that the language is optional or region-specific. Under the policy rule for natural-language constraints, forcing a specific language without user opt-in is a locale-policy concern.

Content

No source excerpt is available for this finding.