Back to skill

Security audit

HiveFence

Security checks for vulnerabilities and agentic risk

Overview

HiveFence is a coherent prompt-injection defense skill, with review notes for automatic threat-hash reporting and unpinned install commands.

Install only in an environment where outbound reporting of prompt-derived threat hashes is acceptable. Prefer a pinned package version or verified release, and confirm whether automatic reporting can be disabled before using it with confidential prompts.

Vulnerability Patterns
  • Insecure DependenciesIntroduces malicious components through unsafe dependency sources
  • 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
Findings (1)

T08 · Insecure Dependencies

Warning
Location
SKILL.md:31
Finding

Unpinned Third-Party Package Installation

Content
View full analysis
Remediation
View remediation
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)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
96% confidence
Finding

The skill states that new attack patterns are 'hashed and submitted to the network' and that reporting can happen automatically, but it does not present a clear, prominent warning about remote transmission of detected content-derived data. Even if only hashes are shared, this is still a privacy and consent issue because users may not expect security-relevant prompt material to be sent to a third-party service, and hashes can still enable correlation, replay matching, or leakage of sensitive repeated inputs. The context makes this more concerning because the skill markets itself as a security/privacy tool, which may lower user suspicion.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
94% confidence
Finding

The installation instructions tell users to execute npx clawhub install hivefence without pinning a specific version of the package manager or intermediary tool. That creates a supply-chain risk: a compromised, replaced, or unexpectedly updated clawhub package could execute arbitrary code during installation before the user ever inspects the skill. In a security-focused skill, this is more dangerous because users are likely to trust and install it quickly based on its defensive branding.

Content

No source excerpt is available for this finding.