Back to skill

Security audit

verify-before-answer

Security checks for vulnerabilities and agentic risk

Overview

This skill tells the agent to verify factual claims before answering and does not include hidden code, persistence, credential access, or destructive behavior.

Install only from a publisher and ClawHub installer version you trust, preferably with a pinned installer version instead of `@latest`. Expect the skill to make the agent search or check documentation more often for factual questions, which can improve accuracy but may add latency and external lookups.

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:39
Finding

Unpinned Third-Party Package Execution in Recommended Installation Command

Content
View full analysis

Vulnerability Details

File Location: README.md:39
Vulnerability Type: Supply-chain risk caused by executing a mutable package version
Risk Level: Medium

Vulnerable Code

bash
npx clawhub@latest install @padepa/verify-before-answer

Technical Analysis

The recommended installation procedure invokes npx with the mutable @latest tag. When a user runs this command, npm may retrieve and execute whatever version of the third-party clawhub package is currently associated with that tag.

Because neither an exact package version nor an integrity digest is specified, the code executed during installation can change after this skill has been reviewed. A compromised publisher account, malicious future release, registry compromise, or dependency-chain compromise could therefore cause the command to execute attacker-controlled package code.

This finding concerns the documented installation path. The audited project itself contains no executable scripts or embedded payloads.

Attack Path

  1. An attacker compromises the clawhub npm publisher, package distribution channel, or a dependency used by a future release.
  2. The attacker publishes a malicious version and causes the mutable latest tag to resolve to it.
  3. A user follows the installation instructions in README.md and runs the documented npx command.
  4. npx downloads and executes the malicious package or its installation/runtime hooks.
  5. The payload runs under the privileges of the user executing the command and can access resources available to that account.

Impact Assessment

Successful exploitation could provide arbitrary code execution with the installing user's privileges. Depending on that user's environment and permissions, an attacker could read or modify user-accessible files, access environment variables and credentials, alter local configuration, install additional payloads, or perform network operations.

The command does not inherently grant administ ...[truncated 232 chars]

Remediation
View remediation

Remediation Suggestions

  1. Replace @latest with an exact, reviewed version:
    bash
    npx clawhub@X.Y.Z install @padepa/verify-before-answer
    
  2. Verify the package's provenance, publisher identity, and release integrity before recommending it.
  3. Where supported, publish and document a cryptographic integrity digest or signed provenance attestation for the approved package artifact.
  4. Review the pinned package version and its transitive dependencies for lifecycle scripts and known vulnerabilities.
  5. Update the pinned version only through a controlled review process rather than allowing installation behavior to change automatically.
  6. Warn users not to execute the installer with elevated privileges unless explicitly required and independently justified.
Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • 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
Findings (4)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

This README says the skill triggers based on broad classes like factual, comparison, or capability questions and explicitly states it only considers question type. Those categories overlap heavily with ordinary user requests, and the file does not provide explicit trigger phrases, exclusions, or negative examples to clarify when the skill should not activate.

Content

No source excerpt is available for this finding.

Rp1

Medium
Category
MCP Rug Pull
Confidence
91% confidence
Finding

The README instructs users to run npx clawhub@latest install ..., which pulls and executes the latest package version at install time. This creates a supply-chain risk: if the package is compromised or a breaking/malicious release is published, users may execute unreviewed code during installation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest description and main instructions are written to direct behavior in Chinese, including explicit Chinese response guidance, without offering the user a language choice or stating that the skill is intended only for Chinese-language contexts. This can violate language/locale policy because it imposes a specific locale by default rather than making it opt-in.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
74% confidence
Finding

Most of the skill description and usage guidance is written in Chinese, with only a brief English summary. For a general-purpose skill README, this can amount to a language policy issue because it does not explicitly offer the user a language or locale choice, nor explain that the skill is intended only for a Chinese-speaking context.

Content

No source excerpt is available for this finding.