Back to skill

Security audit

Yuque 语雀知识库管理

Security checks for vulnerabilities and agentic risk

Overview

The skill matches its Yuque management purpose, but it stores a Yuque token in plaintext, can send that token and document data to a configurable server, and includes destructive actions without built-in confirmations.

Install only if you are comfortable granting an agent access to your Yuque account. Prefer using the YUQUE_TOKEN environment variable instead of config.json, keep any token narrowly scoped if Yuque supports that, verify base_url remains https://www.yuque.com, and require manual confirmation before deleting documents, changing visibility, or reorganizing TOC nodes.

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 (2)

T09 · Insecure Skill Coding Practices

Error
Location
scripts/_client.py:27
Finding

API Token and Document Data Can Be Transmitted to an Arbitrary Configured Server

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Warning
Location
scripts/_client.py:15
Finding

Long-Lived Yuque API Token Is Stored in a Plaintext Project Configuration File

Content
View full analysis
Remediation
View remediation
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
Findings (10)

Credential Access

High
Category
Privilege Escalation
Confidence
70% confidence
Finding

Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.

Content

Scanner excerpt · SKILL.md (reported line 22)May include surrounding context.

md
### How to get your API Token

1. Login to [Yuque](https://www.yuque.com)
2. Click Avatar → Settings (设置) → Developer (开发者) → Personal Access Token (个人访问令牌)
3. Create a new token, copy it

## Setup Details

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/api-reference.md (reported line 104)May include surrounding context.

md
#### PUT /api/v2/repos/{book_id}/docs/{id}
Update a document. Same fields as create, all optional.

#### DELETE /api/v2/repos/{book_id}/docs/{id}
Delete a document.

---

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
80% confidence
Finding

Tool parameters are crafted to achieve unintended or unsafe behavior. Parameter abuse can bypass intended safety checks (e.g. shell=True, --force, dangerous glob patterns).

Content

Scanner excerpt · references/api-reference.md (reported line 148)May include surrounding context.

md
#### PUT /api/v2/repos/{book_id}
Update repo. Fields: `name`, `slug`, `description`, `public`, `toc` (markdown format).

#### DELETE /api/v2/repos/{book_id}
Delete a repo.

---

Undeclared Tool Scope

Medium
Category
MCP Least Privilege
Confidence
91% confidence
Finding

The skill exposes capabilities that can access environment variables, read local files, and make network requests, but it does not declare any explicit tool scope or permission boundaries. In an agent environment, this increases the chance of over-broad execution, unintended data access, or silent exfiltration because the agent may use more privileges than the user expects.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The instructions tell the agent to place a Yuque API token into config.json, creating a plaintext local credential file without any warning about file permissions, accidental commits, or workspace exposure. In shared repos or agent-accessible directories, this can lead to credential theft and unauthorized access to the user's Yuque account and content.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
89% confidence
Finding

The skill documents a delete_doc.py capability but provides no warning, confirmation step, or safeguard for destructive actions. In agent workflows, this can cause irreversible document deletion from ambiguous prompts, operator mistakes, or prompt injection that tricks the agent into invoking deletion.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

The reorganization workflow includes removeNode actions that can alter or remove the visible knowledge-base structure without warning about the consequences. Even if content is not fully deleted, structural changes can hide documents, break navigation, and cause significant operational disruption when executed by an autonomous agent.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
87% confidence
Finding

This markdown API reference includes DELETE endpoints for documents and repositories and update operations that can modify user content, but it provides no warning about their destructive effect or the need for caution. Under the markdown-file criteria, descriptions should warn about behaviors that may affect user data or system integrity.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

This script sends arbitrary document content to Yuque and can optionally set visibility to public or org-public without any explicit user-facing confirmation or warning at the point of transmission. In an agent skill context, that increases the risk of accidental exfiltration of sensitive data or unintended publication if upstream tooling passes private content or sets --public automatically.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The script performs an irreversible DELETE request against a Yuque document immediately after parsing CLI arguments, with no confirmation prompt, dry-run mode, or guardrail to verify the target. In an agent skill context, this increases the chance of accidental or mis-targeted deletion from user misunderstanding, prompt injection into parameters, or automation mistakes, leading to data loss.

Content

No source excerpt is available for this finding.