ClawHub
Back to skill

Security audit

Feishu

Security checks for vulnerabilities and agentic risk

Overview

This Feishu connector is mostly transparent, but its first-time setup tells the agent to run remote installer scripts, so it should be reviewed before use.

Install only if you trust OOMOL and the oo CLI. Prefer manually installing the CLI from vetted documentation instead of letting an agent run the curl|bash or iex commands, and require explicit confirmation for any Feishu write or destructive action.

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
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (3)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The command curl -fsSL https://cli.oomol.com/install.sh | bash fetches code from the network and executes it immediately, giving the remote endpoint full control over the local environment at execution time. In an agent context, this is especially dangerous because a normal Feishu task could be escalated into arbitrary command execution and persistence if the tool is missing or if an attacker manipulates setup conditions.

Content

Scanner excerpt · SKILL.md (reported line 457)May include surrounding context.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

Line L003 says to use this skill for "ANY Feishu request" and "Whenever a task involves Feishu," which is extremely broad and lacks boundaries or exclusion conditions. This can cause unintended invocation for routine mentions of Feishu rather than clearly scoped actions.

Content

No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill instructs the agent to install missing tooling by executing remote shell or PowerShell bootstrap scripts, which expands the skill from Feishu operations into arbitrary code execution on the host. Even though framed as first-time setup, piping a fetched script directly into a shell is a well-known supply-chain risk and is unnecessary for a connector skill that should assume a controlled runtime.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.