Back to skill

Security audit

Ascii Art Generator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward ASCII art helper with no hidden data access, network behavior, persistence, or destructive actions found in the inspected artifacts.

This appears safe to install for ASCII art generation. Prefer a pinned or already-installed ClawHub CLI instead of copy-pasting the unpinned npx command, and review any destination path before asking an agent to save generated art to a file.

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:17
Finding
Unpinned npm Package Execution During Installation## Vulnerability Details **File Location**: `README.md:17-23` **Vulnerability Type**: Unpinned third-party package execution **Risk Level**: Medium **Vulnerable Code:** ```markdown ## Installation ```bash npx clawdhub install ascii-art-generator ``` Or manually install by copying the skill folder to your Clawdbot skills directory. ``` ### Technical Analysis The documented installation command invokes `clawdhub` through `npx` without specifying an exact package version, integrity hash, lockfile, or trusted package source. If the package is not already available locally, `npx` can retrieve it from the configured npm registry and execute its CLI code. Consequently, the code executed during installation is not fully represented by the audited project. Its behavior can change after this project has been reviewed. A compromised publisher account, malicious package release, registry compromise, dependency compromise, or unexpected upstream update could cause arbitrary code to run when a user follows the installation instructions. This finding concerns the unpinned installer dependency. No malicious behavior was identified in the Python scripts shipped in the audited project. ### Attack Path 1. An attacker compromises the npm package, its publisher account, one of its executable dependencies, or the registry resolution path. 2. The attacker publishes or serves a malicious version under the package name `clawdhub`. 3. A user follows the README and runs `npx clawdhub install ascii-art-generator`. 4. `npx` resolves and downloads the unpinned package version from the configured registry. 5. The downloaded package or its dependency code executes with the privileges of the user running the command. 6. The malicious code can access resources available to that user and may alter the installation process or install additional payloads. ### Impact Assessment Successful exploitation could provide arbitrary code execution w ...[truncated 436 chars]
Remediation
## Remediation Suggestions 1. Pin the installer to a specifically reviewed version, for example: ```bash npx --yes clawdhub@<audited-version> install ascii-art-generator ``` 2. Document the expected npm registry, publisher identity, package version, and verification procedure. 3. Verify package integrity using a trusted lockfile, registry integrity metadata, signed provenance, or a published checksum where supported. 4. Prefer a separately installed and administratively approved CLI. If the tool must already be installed, use a mode that prevents network retrieval, such as: ```bash npx --no-install clawdhub install ascii-art-generator ``` 5. Retain the documented manual installation option and provide checksum or signature verification for the Skill archive. 6. Run installation with an unprivileged account in an isolated environment, and avoid exposing unnecessary secrets or credentials to the installer process. 7. Periodically review the pinned package and its transitive dependencies before updating the documented version.
Vulnerability Patterns
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (5)

Rp1

Medium
Category
MCP Rug Pull
Confidence
93% confidence
Finding
The README instructs users to run `npx clawdhub install ascii-art-generator` without pinning a specific package version. Because `npx` resolves and executes packages dynamically, users may install or run a newer or compromised release than intended, creating a supply-chain risk. In the context of a skill installation guide, this is more dangerous because readers are likely to copy-paste the command directly from documentation.

Vague Triggers

Medium
Confidence
93% confidence
Finding
The skill description is very broad ('artistic expression', 'technical diagrams', 'conceptual illustrations', 'when image generation is not available'), which can cause the agent to invoke this skill for many generic creative or formatting requests. Over-broad routing increases the chance of unintended activation, response hijacking, or bypass of more appropriate skills or guardrails, even though the content itself is not directly malicious.

Natural-Language Policy Violations

Low
Confidence
82% confidence
Finding
The example ASCII art includes Chinese text and presents it as part of the skill's inspirational content, but the document does not state that multilingual output is optional or user-selected. This can conflict with language/locale policy expectations if the skill implicitly normalizes a non-user-selected language in generated content.

Missing User Warnings

Low
Confidence
84% confidence
Finding
This markdown file includes guidance to 'output as text or save to file,' which introduces a data-writing action. The surrounding usage instructions do not include any warning or disclosure about overwriting files, choosing safe output paths, or reviewing destination locations.

Natural-Language Policy Violations

Low
Confidence
78% confidence
Finding
The manifest includes an author display name containing Chinese characters alongside English text, which may reflect a fixed language/locale presentation choice in user-visible metadata. Under the policy, forced locale-specific presentation can be a violation when there is no documented user choice or justification.