Back to skill

Security audit

te

Security checks for vulnerabilities and agentic risk

Overview

This skill is a coherent Lobster.fun streaming guide; its network use and public output are expected, but users should handle keys and stream content carefully.

Install only if you are comfortable sending stream content, chat interactions, and media searches to Lobster.fun. Pin or verify the installer when possible, keep API and stream keys secret, and avoid streaming private, personal, or proprietary information.

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:14
Finding
Unpinned Package Execution and Skill Installation## Vulnerability Details **File Location**: `SKILL.md`, lines 14–18 **Vulnerability Type**: Supply-chain exposure through mutable package resolution **Risk Level**: Medium **Vulnerable Code:** ```bash npx clawhub@latest install lobster ``` ### Technical Analysis The installation instructions invoke `clawhub` through `npx` using the mutable `latest` distribution tag. The command does not pin an audited package version or verify the downloaded artifact's integrity or signature. Because `npx` can download and execute the package selected by the registry at invocation time, the effective installer may change after this Skill has been reviewed. A compromised publisher account, package registry, release process, or newly published malicious version could therefore turn the documented installation command into an arbitrary-code execution vector. ### Attack Path 1. An attacker compromises the `clawhub` publishing account, registry entry, or release pipeline, or otherwise causes a malicious release to become the package's `latest` version. 2. The attacker publishes an altered package containing malicious installation or runtime behavior. 3. A user follows the documented command: ```bash npx clawhub@latest install lobster ``` 4. `npx` resolves the mutable `latest` tag and downloads the attacker-controlled release. 5. The downloaded package executes with the privileges and environment of the invoking user. ### Impact Assessment Successful exploitation could permit arbitrary code execution under the invoking user's account. Depending on that account's privileges and environment, the malicious package could access readable files and credentials, alter local files, install modified Skill content, execute network requests, or affect other resources available to the user. The reviewed file does not itself establish privilege escalation, persistence, or an active package compromise; the risk arises from executing a mutab ...[truncated 26 chars]
Remediation
## Remediation Suggestions - Replace `@latest` with an exact, reviewed version, for example: ```bash npx clawhub@X.Y.Z install lobster ``` - Verify the selected release and publisher before documenting or executing it. - Where supported, enforce package integrity using a trusted lockfile, registry integrity hash, checksum, or cryptographic signature. - Use a trusted registry explicitly and protect against dependency confusion or registry substitution. - Review upgrades before changing the pinned version rather than automatically tracking `latest`. - Run the installer with the minimum necessary privileges and avoid executing it as an administrator or root user.
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 (4)

Rp1

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.

External Transmission

Medium
Category
Data Exfiltration
Content
### Register

```bash
curl -X POST https://lobster.fun/api/v1/agents/register \
  -H "Content-Type: application/json" \
  -d '{"name": "YourAgentName", "description": "Your description"}'
```
Confidence
60% confidence
Finding
Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Missing User Warnings

Medium
Confidence
92% confidence
Finding
The skill returns and then repeatedly uses `api_key` and `stream_key` in examples, but only says to save them immediately; it does not explicitly warn users not to share, log, commit, or expose those secrets. In an agent/tooling context, omission of secrecy guidance can lead to credentials being pasted into chat, stored in logs, or embedded in prompts, enabling account takeover or stream hijacking.

Missing User Warnings

Medium
Confidence
90% confidence
Finding
The skill encourages sending stream text, chat interactions, GIF search terms, and YouTube search terms to external services but does not clearly warn that this content leaves the local environment and may be processed by Lobster and third parties. In a live-streaming context, users may unintentionally transmit sensitive, personal, or proprietary information through generated speech or media searches.

Static analysis

No suspicious patterns detected.