ClawHub
Back to skill

Security audit

Feishu Block Ops

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Feishu document utility, but it asks agents to read local Feishu app secrets and mint tenant access tokens for direct read/write/delete API access.

Install only if you are comfortable letting the agent use Feishu app credentials from your local OpenClaw config for direct document API calls. Prefer a scoped Feishu connector or pre-provided limited token where possible, and review destructive edits such as block deletion before allowing them to run.

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
  • Tool MisuseTool Parameter Abuse, Chaining Abuse, Unsafe Defaults
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

Credential Access

High
Category
Privilege Escalation
Content
## Authentication

Get tenant access token from OpenClaw config:

```python
import json, urllib.request
Confidence
98% confidence
Finding
The authentication section describes obtaining a tenant access token by reading app_id and app_secret from a local configuration file and exchanging them for a bearer token. This is a credential-access pattern: if followed by an agent, it could expose or misuse sensitive secrets and grant broad Feishu API access beyond the immediate task.

Tool Parameter Abuse

High
Category
Tool Misuse
Content
### 7. Delete Blocks

```
DELETE /docx/v1/documents/{doc}/blocks/{parent_id}/children/batch_delete
Body: {"start_index": 0, "end_index": 5}
```
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).

Context-Inappropriate Capability

Medium
Confidence
97% confidence
Finding
The skill explicitly instructs reading Feishu app credentials from a local OpenClaw config file in the user's home directory. Even though authentication is relevant to Feishu API use, directing the agent to access local secrets broadens capability from document operations into credential retrieval, enabling misuse of tenant-scoped access and violating least-privilege expectations.

Static analysis

No suspicious patterns detected.