ClawHub
Back to skill

Security audit

Acp Fallback

Security checks for vulnerabilities and agentic risk

Overview

The skill describes a reasonable multi-provider agent fallback workflow, but it relies on a missing relative shell script and automatic provider switching that could execute unintended local code or send task data to additional vendors.

Review before installing. Only use this skill if you control the referenced acp-fallback.sh script and are comfortable with task content being retried through multiple ACP/model providers automatically. Prefer a bundled or pinned implementation with explicit provider opt-in and clear logging behavior.

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)

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The skill documentation instructs agents to use npx acpx without a pinned package version, which can cause execution of whatever package version is current at runtime. If the upstream package is compromised, unpublished/replaced, or introduces unsafe changes, users of the skill may execute unreviewed code during agent operations.

Content

No source excerpt is available for this finding.