Back to skill

Security audit

Boosta Long to Shorts

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward Boosta API helper, with external API and API-key use that match its stated video-processing purpose.

Before installing, prefer the ClawHub package or a pinned commit/release over the unversioned npx/GitHub examples, and only submit video URLs you are allowed to share with Boosta. Store BOOSTA_API_KEY as an environment variable and avoid exposing it in logs or 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
README.md:93
Finding
Unpinned executable dependency and mutable remote installation sources<![CDATA[ ## Vulnerability Details **File Location**: `README.md`, lines 93-120 **Vulnerability Type**: Unpinned executable dependency and mutable supply-chain source **Risk Level**: Medium ### Vulnerable Code ```bash git clone https://github.com/hundevmode/boosta-long-to-shorts-openclaw-skill.git cd boosta-long-to-shorts ``` ```bash npx skills add hundevmode/boosta-long-to-shorts-openclaw-skill --skill boosta-long-to-shorts ``` ```bash npx skills add https://github.com/hundevmode/boosta-long-to-shorts-openclaw-skill --list ``` ### Technical Analysis The installation instructions invoke `npx skills` without an exact package version and retrieve the Skill from a GitHub repository without pinning a commit hash or signed release. Both sources are mutable, so the code executed or installed in the future may differ from the audited artifact. `npx` can download and execute the currently resolved npm package. If that package, its dependencies, or its publishing account is compromised, malicious code could run during installation. Similarly, cloning or installing from the repository’s default branch trusts all subsequent upstream changes. No malicious dependency or compromised upstream source was identified in the audited files. The vulnerability is the absence of version pinning and integrity verification. ### Attack Path 1. An attacker compromises the npm package, one of its dependencies, the package publisher, or the referenced GitHub repository. 2. The attacker publishes a malicious package version or modifies the repository’s default branch. 3. A user follows the README and runs the unversioned `npx skills` command or clones the mutable branch. 4. The compromised CLI or repository content executes or installs with the invoking user’s privileges. 5. The malicious component can access resources available to that user and may install a Skill that influences later agent operations. ### Impact Assessment Successful exploitation could provide code execution ...[truncated 718 chars]
Remediation
<![CDATA[ ## Remediation Suggestions 1. Pin the executable npm package to a reviewed exact version, for example: ```bash npx skills@X.Y.Z add ... ``` 2. Pin GitHub installation references to an audited commit hash or immutable signed release tag rather than the default branch. 3. Publish cryptographic checksums or signatures for release artifacts and document how users should verify them before installation. 4. Use npm lockfiles and integrity metadata wherever package installation is part of the supported workflow. 5. Recommend reviewing downloaded content before execution, particularly before granting access to credentials such as `BOOSTA_API_KEY`. 6. Protect upstream publisher and repository accounts with multi-factor authentication, restricted release permissions, branch protection, and signed commits or releases. ]]>
Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (8)

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.

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.

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.

Lp3

Medium
Category
MCP Least Privilege
Confidence
93% confidence
Finding
The skill requires network access and environment-secret access but does not declare an explicit tool scope such as permissions or allowed-tools. That creates an overbroad execution model where an agent may invoke capabilities beyond what a reviewer or user can easily verify, increasing the risk of unintended secret exposure or unauthorized outbound requests.

Missing User Warnings

Medium
Confidence
89% confidence
Finding
The skill instructs sending user-provided video URLs to a third-party API but does not include a clear user-facing disclosure that the URL and associated processing metadata will be shared with Boosta. This can lead to privacy and compliance issues, especially if the URL contains private, unlisted, tokenized, or otherwise sensitive content.

Missing User Warnings

Medium
Confidence
85% confidence
Finding
This code submits `video_url`, `video_type`, and optional configuration data to the remote Boosta API via `_request`, which performs outbound HTTP calls. While the CLI help describes the command purpose, there is no explicit warning, confirmation, or disclosure in the code about sending user-provided data to an external service.

Missing User Warnings

Low
Confidence
91% confidence
Finding
The README promotes sending video URLs and API-key-authenticated requests to a third-party service but does not clearly warn users that their content metadata and possibly sensitive source links will be shared externally. In an automation/agent context, this can lead to unintentional disclosure of private or proprietary media inputs because users may assume processing is local or not fully appreciate the privacy implications.

Missing User Warnings

Low
Confidence
81% confidence
Finding
The code reads an API key from an environment variable and uses it for authenticated requests, but only reports when the variable is missing. There is no user-facing disclosure that the skill requires and will use a sensitive credential for external API access.

Static analysis

No suspicious patterns detected.