ClawHub
Back to skill

Security audit

PPT Generator

Security checks for vulnerabilities and agentic risk

Overview

This appears to be a presentation-generation skill that uses a disclosed external API and web template assets, with privacy and network-dependency risks but no evidence of hidden, destructive, or deceptive behavior.

Install only if you are comfortable sending the speech or manuscript content you provide to SkillBoss AI and loading CDN-hosted assets in generated HTML. Avoid using it with confidential, regulated, or proprietary material unless you have reviewed the provider's data handling terms and are comfortable with that processing.

SkillSpector

Vulnerability Patterns
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (5)

Description-Behavior Mismatch

Low
Confidence
90% confidence
Finding
The template depends on third-party CDN-hosted JavaScript and fonts, so the generated HTML is not truly self-contained and inherits supply-chain and availability risk from external providers. If a CDN is unavailable, blocked, or serves compromised content, the presentation may fail to render correctly or may execute untrusted code in the viewer's browser.

Missing User Warnings

Medium
Confidence
95% confidence
Finding
The skill explicitly instructs the host agent to send the user's speech/manuscript content to an external LLM API, but it provides no user-facing notice, consent flow, or data handling constraints. This creates a real privacy risk because potentially sensitive user content may be transmitted off-platform without clear disclosure or minimization.

External Transmission

Medium
Category
Data Exfiltration
Content
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

response = requests.post(
    "https://api.skillbossai.com/v1/pilot",
    headers={
        "Authorization": f"Bearer {SKILLBOSS_API_KEY}",
Confidence
93% confidence
Finding
The request configuration shows a full outbound API call with authorization and JSON payload, confirming that skill execution depends on sending data externally. While not inherently malicious, this is a true data exposure risk because the skill context involves processing user speech content that may contain sensitive information.

External Transmission

Medium
Category
Data Exfiltration
Content
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

response = requests.post(
    "https://api.skillbossai.com/v1/pilot",
    headers={
        "Authorization": f"Bearer {SKILLBOSS_API_KEY}",
Confidence
93% confidence
Finding
The request configuration shows a full outbound API call with authorization and JSON payload, confirming that skill execution depends on sending data externally. While not inherently malicious, this is a true data exposure risk because the skill context involves processing user speech content that may contain sensitive information.

External Transmission

Medium
Category
Data Exfiltration
Content
SKILLBOSS_API_KEY = os.environ["SKILLBOSS_API_KEY"]

response = requests.post(
    "https://api.skillbossai.com/v1/pilot",
    headers={
        "Authorization": f"Bearer {SKILLBOSS_API_KEY}",
        "Content-Type": "application/json"
Confidence
91% confidence
Finding
The hardcoded external API domain confirms reliance on a third-party service for content generation. In this skill's context, that increases risk because arbitrary user manuscripts are expected input, so the external transmission can leak proprietary, personal, or confidential presentation material.

Static analysis

No suspicious patterns detected.