ClawHub
Back to skill

Security audit

Huoshan Qifu Knowledge Router

Security checks for vulnerabilities and agentic risk

Overview

This skill is a read-only router for a specific Feishu knowledge catalog and does not show hidden writes, credential theft, or persistence.

Install only if you intend the agent to use your Feishu/Lark account to read this specific internal knowledge catalog and selected linked documents. Review the requested OAuth scopes during authorization and avoid using it for catalogs or documents you do not want the agent to read.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • 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 (2)

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
Take `UpAdbZX4NafHHssmmJgchNrEnyb` as `app_token` and `tblb40YEYGtLsGvu` as `table_id`. Do not restrict retrieval to `vewya09oBp`; that view shows child details and is not the complete catalog.

If the user explicitly supplies another Bitable catalog URL, use it only for that request. Never embed or expose access tokens, app secrets, cookies, device codes, or credentials.

Request these fields:

Autonomous Decision Making

Medium
Category
Excessive Agency
Confidence
75% confidence
Finding

Skill enables autonomous high-impact decisions without human-in-the-loop verification. Critical operations (destructive commands, financial transactions, data deletion) should require explicit user confirmation.

Content

Scanner excerpt · SKILL.md (reported line 12)May include surrounding context.

md
## Default catalog

Use this catalog without asking the user for a URL:

`https://bytedance.larkoffice.com/base/UpAdbZX4NafHHssmmJgchNrEnyb?table=tblb40YEYGtLsGvu&view=vewya09oBp`

Static analysis

No suspicious patterns detected.