ClawHub
Back to skill

Security audit

Feishu Ingest

Security checks for vulnerabilities and agentic risk

Overview

This skill does what it claims: it reads authorized Feishu content and writes selected knowledge-base pages to a configured Gitea repo.

Install only if you intend this agent to read Feishu group history, message attachments, cloud docs, sheets, and bitables, then write selected pages and archived source files into a configured Gitea knowledge-base repo. Use a dedicated Feishu app, minimally scoped Gitea bot token, and a dedicated OPENCLAW_SHARED_DIR because the skill caches a Feishu token and temporary ingest artifacts there.

SkillSpector

Vulnerability Patterns
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (1)

Lp3

Medium
Category
MCP Least Privilege
Confidence
95% confidence
Finding
The skill declares substantial capabilities—environment variable access, filesystem read/write, and network access to Feishu and Gitea—but does not expose any explicit permissions model or scope limitations in the skill declaration. This creates a real security issue because operators and reviewers cannot easily tell what the skill is allowed to access, increasing the risk of over-privileged execution, secret misuse, unintended repository writes, or broad data exfiltration if the implementation or downstream prompts are compromised.

Static analysis

No suspicious patterns detected.