Back to skill

Security audit

claw-turbo

Security checks for vulnerabilities and agentic risk

Overview

This skill is openly a fast command router, but it installs unreviewed remote code and can turn ordinary chat phrases into immediate shell or service-management commands without clear safety gates.

Review carefully before installing. Only use this behind strong local access controls, pin and verify the implementation source, avoid raw shell templates, require explicit command prefixes and confirmations for state-changing routes, and run the proxy as a dedicated low-privilege user.

Vulnerability Patterns
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
  • 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
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
Findings (2)

T03 · Remote Payload Retrieval and Execution

Error
Location
SKILL.md:58
Finding

Unpinned Remote Source Is Retrieved and Installed as a Trusted Proxy

Content
View full analysis
Remediation
View remediation

T09 · Insecure Skill Coding Practices

Error
Location
routes.example.yaml:50
Finding

User-Controlled Message Data Is Inserted into Shell Command Templates

Content
View full analysis
...) # - command: bash command template (use {{raw_message}}, {{capture_name}}) # - response_template: response sent back to the user ``` A supplied example inserts the entire user message into a command: ```yaml - name: print-document description: "Print a document by ID" patterns: - 'print\s+(?P[A-Z]{4}\d{7})' - '打印\s*(?P[A-Z]{4}\d{7})\s*(的)?\s*(资料|全部|所有)' command: 'bash /path/to/your/skill/run.sh "{{raw_message}}"' response_template: "Printed document {{doc_id}}" ``` Other examples use captured data in privileged operational commands: ```yaml - name: restart-service description: "Restart a running service" patterns: - 'restart\s+(?P[\w-]+)' - '重启\s+(?P[\w-]+)' command: 'systemctl restart {{service}}' response_template: "Restarted {{service}}" ``` ### Technical Analysis The documented command model uses textual substitution to place message-derived values into Bash command strings. Quoting `{{raw_message}}` with double quotes does not constitute safe shell escaping. If a substituted message can contain a double quote, command substitution, backticks, or other shell syntax, it may terminate or alter the intended argument and cause the shell to interpret additional operations. The example regex validates the captured `doc_id`, b ...[truncated 2323 chars]
Remediation
View remediation
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 (9)

Missing User Warnings

High
Category
Not specified by scanner
Confidence
94% confidence
Finding

The description emphasizes speed and perfect execution while omitting any warning that matched inputs can directly execute scripts and operational commands without LLM mediation. This can mislead users into deploying the middleware in front of an LLM without appreciating that it creates an immediate command-execution path for matched phrases.

Content

No source excerpt is available for this finding.

Missing User Warnings

High
Category
Not specified by scanner
Confidence
96% confidence
Finding

The examples show direct shell execution and service-management commands like 'bash /opt/scripts/deploy.sh {{service}} staging' and 'systemctl restart {{service}}' without adjacent warnings about authorization, validation, shell-safety, or operational blast radius. In context, this is especially dangerous because the product's core feature is bypassing LLM inference and executing matched commands immediately, so readers may copy unsafe patterns into production.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The skill is explicitly designed to intercept natural-language commands like deploy, restart, print, and check logs using regex and bypass LLM validation entirely. Because these are common conversational phrases and the documentation does not describe strong namespace, confirmation, or context constraints, normal user text could be misclassified as an executable command and trigger operational actions unexpectedly.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

The use-case examples include very generic phrases such as 'restart nginx', 'turn on lights', and 'refund order ORD-789', which are plausible in ordinary conversation and could overlap with benign chat. In a middleware that automatically executes scripts on regex match, this broad trigger surface materially increases the chance of unintended execution of destructive or sensitive actions.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
84% confidence
Finding

This route maps a natural-language deploy command directly to a production-capable shell action with no confirmation, approval gate, or visible safety interlock. In a zero-latency router that bypasses LLM reasoning, accidental matches or unauthorized use can trigger immediate high-impact operational changes, including production deployments.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
88% confidence
Finding

The restart-service route activates on a very short pattern like 'restart ' (and its Chinese equivalent) without additional context, exclusions, or channel constraints. In a manifest-style routing file, this can cause unintended invocation because the trigger is a common imperative phrase rather than a narrowly scoped command form.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
86% confidence
Finding

The configuration performs an immediate 'systemctl restart' from a simple chat-style command without warning or confirmation. Given the skill's design goal of intercepting known commands and executing directly, this increases the chance of disruptive service restarts from mistaken input or insufficiently authorized users.

Content

No source excerpt is available for this finding.

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
83% confidence
Finding

The generate-report route allows broad verbs like 'generate', 'create', and especially 'run' followed by 'report ', which can be interpreted in multiple everyday contexts. The file does not provide exclusion conditions or narrower activation guidance to distinguish intentional routing from normal conversation.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
71% confidence
Finding

Several routes embed English and Chinese trigger patterns directly, but the file does not explain whether multilingual activation is intentional, configurable, or user-selectable. If organizational policy requires user opt-in for language or locale handling, this undocumented hard-coding may violate that expectation.

Content

No source excerpt is available for this finding.