Back to skill

Security audit

EDI MSP Toolkit

Security checks for vulnerabilities and agentic risk

Overview

This skill is a sparse MSP toolkit description with some operational and supply-chain cautions, but no artifact-backed evidence of hidden or malicious behavior.

Before installing, verify the intended clawhub package source and version, avoid running npm installs with elevated privileges, and treat any reset/reboot function as an opt-in administrative action that may interrupt service.

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:12
Finding
Unpinned npm Dependency Introduces Supply-Chain Risk## Vulnerability Details **File Location**: `SKILL.md`, line 12 **Vulnerability Type**: Unpinned and unaudited third-party dependency installation **Risk Level**: Medium **Code Snippet**: ```text ## Setup npm install clawhub clawhub publish /home/cc/.openclaw/workspace/skills/msp-toolkit ``` ### Technical Analysis The setup instructions install the `clawhub` npm package without specifying an exact version, lockfile, or integrity hash. Consequently, the package content retrieved when the command is run may differ from the content available when the skill was audited. npm packages can define installation lifecycle scripts, such as `preinstall`, `install`, and `postinstall`, which npm may execute automatically. If the package or one of its transitive dependencies is compromised, replaced, or maliciously updated, following this instruction could execute attacker-controlled code. The audited project does not include the dependency source, a package manifest, or a lockfile with which to verify its behavior or provenance. There is no evidence in the reviewed file that the named package is currently malicious. The vulnerability is the unsafe reliance on a mutable, externally maintained dependency without version or integrity controls. ### Attack Path 1. An attacker compromises the `clawhub` npm package, its maintainer account, or a transitive dependency. 2. The attacker publishes a malicious release or introduces a malicious npm lifecycle script. 3. A user follows the setup instruction and runs `npm install clawhub`. 4. npm retrieves the mutable package release and resolves its dependency tree. 5. Malicious lifecycle code executes with the permissions of the user running npm. 6. Depending on those permissions, the payload could access user-readable files, modify the workspace, steal available credentials or tokens, or establish additional malicious behavior. ### Impact Assessment Successful exploitation could provide ...[truncated 550 chars]
Remediation
## Remediation Suggestions 1. Pin `clawhub` to an exact, reviewed version rather than installing the latest mutable release. 2. Add a package manifest and committed lockfile containing registry-resolved integrity metadata. 3. Use `npm ci` for reproducible installations after validating the lockfile. 4. Prefer `npm ci --ignore-scripts` when package lifecycle scripts are not required. 5. If lifecycle scripts are necessary, audit them and all relevant transitive dependencies before permitting execution. 6. Verify the package's registry provenance, maintainer identity, signatures or attestations where available, and published integrity values. 7. Run dependency installation as an unprivileged user in an isolated environment with no production credentials. 8. Document the expected package version and checksum in `SKILL.md`.
Vulnerability Patterns
  • 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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
Findings (1)

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill advertises a reboot/reset script (`nuc-reset.sh`) but provides no warning that running it is disruptive and can immediately interrupt service, disconnect users, or affect managed infrastructure. In an MSP context, operators may invoke toolkit actions quickly during troubleshooting, so undocumented disruptive behavior increases the chance of accidental outages.

Static analysis

No suspicious patterns detected.