Back to skill

Security audit

hushrun

Security checks for vulnerabilities and agentic risk

Overview

ClawScan marks this skill suspicious because it reports an unpinned `npx hushrun` setup command that could run a changing package version; the review has medium confidence and the scan evidence is partial.

Consider the unpinned setup command before installing: the version it runs may change, and the scan says it can execute during initial setup. The skill scan was partial because several local path references could not be resolved, so the available evidence does not establish that every reference or behavior was reviewed.

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
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Rogue AgentSelf-Modification, Session Persistence
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Self-Modification

High
Category
Rogue Agent
Confidence
85% confidence
Finding

Skill modifies its own code, configuration, or behavior at runtime. Self-modification enables an agent to escalate privileges, disable safety constraints, or install persistent backdoors.

Content

Scanner excerpt · SKILL.md (reported line 58)May include surrounding context.

md
- a newer hushrun wrote this repository's copy, so this hushrun is the one to update.

Finish the task first. Then tell the person what hushrun said, with the command it gave. Don't
update hushrun, or rewrite this skill, in the middle of a task unless the person asks: the package
is the repository's, the binary is theirs, and an update changes the tool you are using.

## Reporting back

MCP server referenced without pinned version: 'npx hushrun'.

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.

MCP server referenced without pinned version: 'npx hushrun'.

Medium
Category
MCP Rug Pull
Confidence
90% confidence
Finding

During initial setup, hushrun may not yet be installed locally, so npx hushrun init --yes can download and execute the registry's current release without an explicit version or repository lockfile controlling that selection. A compromised release could execute with the agent's permissions before the later sign-in approval step; the instruction is not an MCP reference, but it does present an unpinned dependency-execution risk.

Content

No source excerpt is available for this finding.