Plant Fiber Cordage Making Basics

• Outcome: Pass
• Latest audit: Sep 16, 2026 · 4:30 AM UTC
• Version: 1.0.0

Overview

This skill is a coherent plant-fiber cordage guide, with disclosed logging and photo/location use, but users should review the unpinned install command and safety limits.

Install only from a trusted ClawHub source, prefer a pinned or verified CLI version when available, and be cautious about sharing precise location or plant photos. Treat plant identification and load-bearing claims as advisory; verify plants and test cordage safely before relying on it.

A.I.G

Vulnerability Patterns

• Insecure Dependencies: Introduces malicious components through unsafe dependency sources
• Skill Instruction Hijacking: Alters the agent's session goals or safety constraints when the skill loads
• Agent Memory Poisoning: Writes attacker-controlled rules into memory that affect later sessions
• Remote Payload Retrieval and Execution: Fetches external code whose behavior can change after review
• Embedded Malicious Code: Ships malicious scripts inside the skill and executes them locally

Findings (1)

T08 · Insecure Dependencies

Warning

• Location: SKILL.md:15

Finding

Unpinned Package Execution Through npx

Content

View full analysis

Vulnerability Details

File Location: SKILL.md, lines 15 and 23
Vulnerability Type: Unpinned third-party package execution
Risk Level: Medium

Vulnerable Code

Line 15:

yaml

install: "npx clawhub install plant-fiber-cordage-making-basics"

Line 23:

shell

npx clawhub install plant-fiber-cordage-making-basics

Technical Analysis

The installation instructions invoke clawhub through npx without specifying an exact package version or verifying package integrity. If the package is not already available locally, npx can resolve it from the configured package registry and execute the downloaded package.

Because neither a version nor an integrity hash is provided, the effective executable may change after this skill has been reviewed. The project also contains no lockfile or vendored installer that would establish the precise package artifact expected to run. This creates a supply-chain trust boundary in which compromise of the package, its publisher account, its dependencies, or the configured registry could result in execution of attacker-controlled code.

Attack Path

1. An attacker compromises the package publisher, registry distribution channel, or a transitive dependency used by the package resolved as clawhub.
2. The attacker publishes a malicious package version or modifies the package's installation or runtime behavior.
3. A user follows either documented command and runs npx clawhub install plant-fiber-cordage-making-basics.
4. npx resolves and downloads the unpinned package from the configured registry.
5. The downloaded package binary or applicable lifecycle behavior executes under the invoking user's account.
6. The malicious code can access resources available to that account and alter the local environment before or during skill installation.

Exploitation depends on compromise or malicious control of the external package supply chain; the reviewed file ...[truncated 811 chars]

Remediation

View remediation

Remediation Suggestions

1. Pin clawhub to an audited exact version rather than resolving the latest available release, for example:

   shell

   npx --yes clawhub@X.Y.Z install plant-fiber-cordage-making-basics
   

2. Verify the selected package version and its transitive dependencies before publishing the installation instructions.

3. Use a lockfile and registry integrity metadata where the installation workflow permits them.

4. Document the expected package registry and reject installation from untrusted or unexpected registry configurations.

5. Prefer a locally installed, version-locked CLI over downloading and immediately executing a package at installation time.

6. Run installation with the least-privileged user possible and never recommend elevated execution.

7. Periodically review and deliberately update the pinned version rather than accepting package changes automatically.

SkillSpector

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code
• Trigger Abuse: Overly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access

Findings (4)

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 89% confidence

Finding

The description says to use the skill for broad needs like hauling, binding loads, building shelters, fishing lines, or trade goods whenever commercial rope is unreliable or unavailable. This scope is expansive and overlaps with many general survival or DIY situations without clearly constraining when this specific skill should activate instead of other rope-, shelter-, or fishing-related skills.

Content

No source excerpt is available for this finding.

Rp1

Medium

• Category: MCP Rug Pull
• Confidence: 95% confidence

Finding

The skill instructs users to install and run an external package via npx clawhub install ... without pinning a specific version. This creates a supply-chain risk: a later compromised or malicious release of the referenced package could be fetched and executed implicitly, especially because npx commonly resolves the latest available version.

Content

No source excerpt is available for this finding.

Rp1

Medium

• Category: MCP Rug Pull
• Confidence: 95% confidence

Finding

A second unpinned npx clawhub install ... invocation repeats the same supply-chain exposure in the body of the skill. Repetition increases the chance that an agent or user will execute it directly, pulling whatever version is current at execution time rather than a reviewed, known-good release.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium

• Category: Not specified by scanner
• Confidence: 92% confidence

Finding

The 'Deploy this skill when' section lists broad scenarios like wanting zero-plastic alternatives, custom-length cord, renewable sources, or a micro-business, but it does not define a precise trigger phrase set or clear exclusion conditions. Although there is one 'Do not use' note, it addresses plant identification and water access rather than distinguishing this skill from adjacent crafting, survival, or barter tasks.

Content

No source excerpt is available for this finding.