ClawHub
Back to skill

Security audit

v2ex

Security checks for vulnerabilities and agentic risk

Overview

This is a straightforward V2EX API documentation skill, with expected token use and a documented notification delete endpoint but no hidden execution or persistence.

Install only if you want an agent to use your V2EX API token. Store the token outside code, prefer the least-privileged token available, and require explicit confirmation before deleting notifications.

A.I.G

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

SkillSpector

Vulnerability Patterns
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

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 18)May include surrounding context.

md
## Authentication

V2EX API 2.0 requires a Personal Access Token for authentication.

1. Visit https://www.v2ex.com/settings/tokens to create a token
2. Use the token in the Authorization header: `Authorization: Bearer <your-token>`

Tool Parameter Abuse

High
Category
Tool Misuse
Confidence
90% confidence
Finding

Exposing a parameterized DELETE endpoint without safety constraints can enable tool parameter abuse, especially if an agent is allowed to act on user-supplied or inferred notification IDs. This can lead to unauthorized or unintended deletion of notifications if the action is triggered without validation and confirmation.

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

Delete a Notification

text
DELETE /notifications/:notification_id

Example:

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 210)May include surrounding context.

md
## Best Practices

1. Store Personal Access Tokens securely (environment variables, not in code)
2. Handle rate limits by checking headers and implementing backoff
3. Cache responses when appropriate to reduce API calls
4. Use pagination for endpoints that support it

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 219)May include surrounding context.

md
## Best Practices

1. Store Personal Access Tokens securely (environment variables, not in code)
2. Handle rate limits by checking headers and implementing backoff
3. Cache responses when appropriate to reduce API calls
4. Use pagination for endpoints that support it

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

The skill documents a destructive DELETE operation for notifications but provides no warning, confirmation step, or guidance about irreversible effects. In an agent setting, this increases the chance that an automated workflow could remove user data unintentionally or without explicit consent.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.