Security audit

飞书新机器人创建

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Feishu bot setup workflow, but it asks the agent to handle app secrets and copy personal/workspace memory into a new bot workspace without enough safeguards.

Review this skill before installing. Use a secret manager, environment variable, or protected input path instead of pasting APP SECRET into chat, and avoid storing secrets in plaintext openclaw.json unless file permissions and rotation procedures are clear. Also review and minimize any USER.md, MEMORY.md, AGENTS.md, or TOOLS.md content before copying it into a new bot workspace.

A.I.G

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: SKILL.md:22
Finding: Insecure Collection and Storage of Feishu Application Credentials
Content: View full analysis
Remediation: View remediation

other

Warning

Location: SKILL.md:44
Finding: Unrestricted Replication of User, Agent, and Persistent Memory Data
Content: View full analysis
Remediation: View remediation

SkillSpector

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 (2)

Missing User Warnings

High

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill explicitly asks the user to send APP ID and APP SECRET to the agent without any warning about secure handling, minimization, masking, storage, or safer transfer methods. In this context the risk is elevated because those credentials are then used alongside local config modification and gateway integration, so disclosure or mishandling could enable unauthorized bot control or compromise of the surrounding environment.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 89% confidence
Finding: The trigger phrases are broad enough to activate on ordinary requests like creating or adding a bot, which can cause the skill to run in situations where the user did not intend this specific workflow. In this skill, accidental activation is more dangerous because the workflow leads quickly into credential collection, local filesystem changes, configuration edits, and service restarts.
Content: No source excerpt is available for this finding.