Back to skill

Security audit

KnowMine

Security checks for vulnerabilities and agentic risk

Overview

This is a coherent remote memory/search skill, but users should treat it as a cloud personal-knowledge service and be careful about what they save.

Install only if you are comfortable sending selected notes, memories, and profile-like summaries to KnowMine for remote storage and semantic search. Avoid saving secrets, credentials, regulated data, or highly sensitive personal information, and prefer a pinned installer version instead of `@latest` when available.

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:46
Finding
Unpinned Third-Party Package Execution via npx<![CDATA[ ## Vulnerability Details **File Location**: `SKILL.md`, line 46 **Vulnerability Type**: Unpinned and mutable third-party dependency execution **Risk Level**: Medium ### Vulnerable Code ```bash npx clawhub@latest install knowmine ``` ### Technical Analysis The documented installation command instructs users to invoke `npx` with the mutable `latest` tag. Depending on the local npm environment, `npx` may retrieve the selected package release from the configured npm registry and execute its code immediately. Because neither an exact package version nor an integrity value is specified, the code executed by users can change after this Skill has been reviewed. A future compromised, malicious, or unintentionally vulnerable release selected by `latest` would therefore be executed without corresponding review of this repository. This is a supply-chain weakness rather than evidence that the current `clawhub` package is malicious. Exploitation requires the user to run the documented command and an attacker to control or compromise the relevant package, maintainer account, registry response, or release pipeline. ### Attack Path 1. An attacker compromises the `clawhub` package maintainer account, publishing pipeline, package registry, or another component capable of controlling the release referenced by `latest`. 2. The attacker publishes a malicious package version and assigns or causes the `latest` tag to resolve to that version. 3. A user follows the setup instructions and runs: ```bash npx clawhub@latest install knowmine ``` 4. `npx` downloads the attacker-controlled version from the configured registry. 5. Package lifecycle behavior or the package entry point executes with the privileges of the user who invoked the command. 6. The payload can access resources available to that user, subject to operating-system permissions and environmental restrictions. ### Impact Assessment Successful exploitation could allow arbitrary code execution under ...[truncated 748 chars]
Remediation
<![CDATA[ ## Remediation Suggestions 1. Replace the mutable `latest` tag with an exact, reviewed package version: ```bash npx clawhub@<AUDITED_EXACT_VERSION> install knowmine ``` 2. Do not use version ranges or distribution tags for security-sensitive installation instructions. 3. Where supported, verify the downloaded package using a published integrity hash, signature, provenance attestation, or trusted release checksum. 4. Document the expected package publisher, registry, exact version, and verification procedure so users can detect dependency confusion or registry substitution. 5. Review the selected package version, including lifecycle scripts and transitive dependencies, before recommending it. 6. Update the pinned version only through a controlled dependency-review process. 7. Advise users not to run the installer with administrative privileges and to use an isolated environment where practical. 8. In CI environments, use a lockfile or equivalent immutable dependency resolution and restrict installation-time network access to approved registries. ]]>
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (3)

Vague Triggers

Medium
Confidence
91% confidence
Finding
The description uses broad activation cues such as remembering things across conversations, saving notes, and carrying context between AI platforms, which could trigger the skill during ordinary user discussion rather than an explicit request to use a remote memory service. Because this skill has network access and persists user data, overbroad invocation increases the chance of unintentional transmission of sensitive information.

Missing User Warnings

Medium
Confidence
93% confidence
Finding
The skill encourages saving memories, notes, reflections, and generating profile summaries on a remote MCP server, but it does not prominently warn that conversation-derived content may be transmitted to and stored by an external service. In this context, the omission is especially risky because the skill is designed to accumulate personal knowledge over time, which can include sensitive personal, professional, or credential-adjacent information.

Rp1

Medium
Category
MCP Rug Pull
Confidence
84% confidence
Finding
The installation instruction uses `npx clawhub@latest install knowmine`, which pulls and executes the latest published package at runtime without pinning to a reviewed version. If the upstream package is compromised or a malicious release is published, users could execute attacker-controlled code during installation.

Static analysis

No suspicious patterns detected.