ClawHub
Back to skill

Security audit

Bilibili

Security checks for vulnerabilities and agentic risk

Overview

The skill is coherent for managing Bilibili through OOMOL, but its setup fallback tells agents to run unverified remote installer scripts.

Review the OOMOL CLI installation path before installing. Prefer official installation documentation, pinned releases, and checksum or signature verification, and do not let an agent run the remote installer automatically. For Bilibili actions, only approve write or delete operations after checking the exact target and payload.

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
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

External Script Fetching

High
Category
Supply Chain
Confidence
97% confidence
Finding

The skill instructs the agent/user to install software by piping a remotely fetched script directly into a shell (curl ... | bash). This creates a remote-code-execution path with no integrity verification, pinning, or manual review, so a compromised host, MITM, or malicious update to the installer would execute arbitrary code on the machine. In this skill context, the command appears in a fallback setup flow, which makes it especially risky because an automated agent may follow it when normal execution fails.

Content

Scanner excerpt · SKILL.md (reported line 82)May include surrounding context.

Static analysis

No suspicious patterns detected.