ClawHub
Back to skill

Security audit

dash-cog

Security checks for vulnerabilities and agentic risk

Overview

This skill appears to be a legitimate dashboard generator, but it can send prompts and uploaded datasets to an external SkillBoss API without clear privacy warnings for sensitive data.

Review this skill before installing if you may use real business, employee, customer, financial, log, or regulated data. Use only synthetic, anonymized, minimized, or approved data unless you are comfortable sending the prompt and included dataset content to SkillBoss's external API, and keep the API key in an environment variable or secret manager.

A.I.G

Vulnerability Patterns
  • 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
  • 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)

T09 · Insecure Skill Coding Practices

Warning
Location
SKILL.md:40
Finding

Potential Disclosure of Sensitive User Data to a Third-Party API

Content
View full analysis
Remediation
View remediation

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (6)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
90% confidence
Finding

The manifest description lists a wide range of capabilities such as dashboards, apps, charts, data explorers, and games without defining narrow activation phrases or scope constraints. In a markdown/manifest context, this breadth can create ambiguous invocation conditions and increase the chance of unintended triggering from everyday requests about building apps or visualizations.

Content

No source excerpt is available for this finding.

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
97% confidence
Finding

The skill explicitly instructs users to send prompts and potentially uploaded files or inline datasets to a third-party API, but it does not disclose that user data will leave the local environment. This creates a real data-handling and privacy risk because users may provide sensitive business, employee, financial, or log data without informed consent or minimization.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

This finding identifies the same outbound request where the Authorization header and request body are sent to an external API endpoint. While using an API key in an HTTPS header is normal, the skill still transmits user-supplied content externally and does so without safety notices or data-classification guidance.

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

md
" For complex apps: plan the component structure first, then implement each section "
            "with full interactivity, animations, and polished UX."
        )
    result = requests.post(
        "https://api.heybossai.com/v1/pilot",
        headers={
            "Authorization": f"Bearer {SKILLBOSS_API_KEY}",

External Transmission

Medium
Category
Data Exfiltration
Confidence
95% confidence
Finding

This finding identifies the same outbound request where the Authorization header and request body are sent to an external API endpoint. While using an API key in an HTTPS header is normal, the skill still transmits user-supplied content externally and does so without safety notices or data-classification guidance.

Content

Scanner excerpt · SKILL.md (reported line 50)May include surrounding context.

md
" For complex apps: plan the component structure first, then implement each section "
            "with full interactivity, animations, and polished UX."
        )
    result = requests.post(
        "https://api.heybossai.com/v1/pilot",
        headers={
            "Authorization": f"Bearer {SKILLBOSS_API_KEY}",

External Transmission

Medium
Category
Data Exfiltration
Confidence
94% confidence
Finding

The hardcoded external domain confirms that generated dashboards and app requests are processed by a remote service outside the user's environment. This is materially risky in a dashboard-building skill because example use cases include employee data, financial metrics, logs, and surveys, all of which can be sensitive if transmitted without clear consent and controls.

Content

Scanner excerpt · SKILL.md (reported line 51)May include surrounding context.

md
"with full interactivity, animations, and polished UX."
        )
    result = requests.post(
        "https://api.heybossai.com/v1/pilot",
        headers={
            "Authorization": f"Bearer {SKILLBOSS_API_KEY}",
            "Content-Type": "application/json"

Missing User Warnings

Low
Category
Not specified by scanner
Confidence
82% confidence
Finding

The skill requires an API key and shows how to export it, but provides no guidance on secure credential handling. This increases the chance of accidental exposure through hardcoding, logging, screenshots, shared shell history, or inclusion in generated artifacts and support messages.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.