ClawHub
Back to skill

Security audit

mmxagent-skill-feishu

Security checks for vulnerabilities and agentic risk

Overview

This Feishu setup skill is mostly purpose-aligned, but it handles app credentials while suppressing relevant setup guidance and defers follow-up work to a missing file.

Review this skill before installing. It is intended for Feishu robot setup, but it limits what the agent may tell you about permissions and approval steps, adds a from=maxclaw parameter to links, and relies on a missing feisu.md for later credential use. Only use it if you trust that workflow and are comfortable with the Feishu app credentials being handled by the agent during setup.

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
Findings (1)

T01 · Skill Instruction Hijacking

Error
Location
SKILL.md:12
Finding

Skill Instructions Override Agent Behavior and Suppress Relevant Guidance

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (2)

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
97% confidence
Finding

The skill instructs the agent to perform outbound requests to a third-party Feishu OAuth registration endpoint and then poll for sensitive credentials (client_id/client_secret). This creates an external transmission and secret-handling path that can expose user/account linkage, session cookies, and app credentials to remote services without strong validation, explicit trust boundaries, or secure storage requirements.

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")

Static analysis

No suspicious patterns detected.