Back to skill

Security audit

Video Caption Ai Skill

Security checks for vulnerabilities and agentic risk

Overview

This skill is a simple caption-generation instruction package with a standard but unpinned install command users should treat cautiously.

Before installing, consider pinning or verifying the ClawHub installer version if your environment is sensitive. Expect the skill to work on user-supplied video/caption content and review any generated captions before publishing, especially engagement-oriented phrases.

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:5
Finding

Unpinned Package Execution Through npx

Content
View full analysis

Vulnerability Details

File Location: README.md, lines 5-8
Vulnerability Type: Unpinned third-party package execution
Risk Level: Medium

markdown
## Install
```bash
npx clawhub install video-caption-ai
text

### Technical Analysis

The documented installation command invokes the unversioned `clawhub` npm package through `npx`. If the package is not available locally, `npx` may download and execute the version currently resolved by the configured npm registry. The command does not pin the CLI version, the installed skill version, or an integrity digest.

Consequently, the code executed by users is not fully determined by the audited repository. A compromised registry account, malicious package replacement, dependency compromise, or unexpected future release could cause the installation command to execute code that was not present during this audit.

### Attack Path

1. An attacker compromises the `clawhub` package, one of its transitive dependencies, its publishing account, or the package source used by the configured registry.
2. The attacker publishes a malicious version that satisfies the unversioned package resolution.
3. A user follows the README and runs `npx clawhub install video-caption-ai`.
4. `npx` retrieves the mutable package version from the registry and executes it locally.
5. The malicious package runs with the permissions of the invoking user and may also install further mutable content.

This attack path depends on compromise or malicious replacement of the external package supply chain; the reviewed files do not themselves contain a malicious payload.

### Impact Assessment

Successful exploitation could allow arbitrary code execution with the privileges of the user running the installation command. Depending on that user's access, the payload could read or modify user-accessible files, obtain credentials available to the process, alter development artifacts, o
...[truncated 151 chars]
Remediation
View remediation

Remediation Suggestions

  • Pin the clawhub CLI to a reviewed, trusted version rather than relying on the registry's current resolution.
  • Pin the installed skill to a specific immutable version or content digest where supported.
  • Use package-locking and integrity verification mechanisms to validate the CLI and all transitive dependencies.
  • Document the expected package registry and trusted publisher so users can detect source substitution.
  • Prefer installing and reviewing the pinned package before execution instead of directly executing newly downloaded registry code.
  • Establish a controlled update process that reviews and tests new package versions before changing documented pins.
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 (2)

Rp1

Medium
Category
MCP Rug Pull
Confidence
95% confidence
Finding

The README instructs users to run npx clawhub install video-caption-ai without pinning a specific clawhub version, which means the latest published package will be fetched and executed at install time. If the upstream package is compromised, typosquatted, or changes behavior unexpectedly, users could execute untrusted code during installation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
80% confidence
Finding

The description says the skill 'Supports ... multilingual caption creation in Chinese, English, Japanese, and Korean,' which establishes a language scope but does not explicitly say the user can choose the language or locale. Because the policy asks to flag language/locale constraints when they are forced without opt-in, this is a mild natural-language policy concern.

Content

No source excerpt is available for this finding.