Back to skill

Security audit

Feishu Connect 1.0.0

Security checks for vulnerabilities and agentic risk

Overview

This Feishu connection skill is purpose-aligned, but it makes the agent handle Feishu app secrets without clear secure-handling or warning instructions.

Review before installing if you are comfortable letting the agent obtain and use Feishu App ID/App Secret during setup. Treat the client_secret as sensitive, avoid sharing it in chat when possible, and prefer a setup path that stores credentials locally or redacts them from logs.

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
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Ssd 3

High
Category
Not specified by scanner
Confidence
99% confidence
Finding

The skill explicitly tells the agent to poll for client_id/client_secret, retain them, and continue operating with those credentials in later steps. That creates a clear secret-handling vulnerability: the agent becomes a credential broker and persistent holder of app secrets, increasing risk of leakage through conversation memory, logs, tool traces, or misuse in later actions.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The activation scope is broad: requests about connecting, binding, creating, or integrating Feishu all trigger a flow that obtains credentials and continues setup. Broad triggers increase the chance the agent invokes this sensitive workflow in situations where the user did not clearly intend credential collection or external account linking.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
70% confidence
Finding

npx commands without a version suffix (e.g. @1.0.0) create a rug-pull risk if the upstream server is compromised and publishes a malicious update.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · SKILL.md (reported line 36)May include surrounding context.

md
rm -f "$COOKIE_JAR"

# init
INIT_RESP=$(curl -s -c "$COOKIE_JAR" -b "$COOKIE_JAR" \
  -X POST "https://accounts.feishu.cn/oauth/v1/app/registration" \
  -H "Content-Type: application/x-www-form-urlencoded" \
  -d "action=init")

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs the agent to obtain client_id and client_secret and proceed with them, but it never requires a user-facing warning that these are sensitive credentials. This can lead to accidental exposure in chat history, logs, or downstream tools, and users may not understand the risk of sharing or storing these secrets through the agent.

Content

No source excerpt is available for this finding.