ClawHub
Back to skill

Security audit

PPTMagic Official PPT Creator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed presentation-generation helper that sends slide content to a public PPTMagic service, with no hidden local code, persistence, or unrelated privileges found.

Before installing, understand that deck prompts, outlines, slide descriptions, and uploaded template images may be sent to a public external PPTMagic deployment. Avoid confidential, regulated, or sensitive material unless you trust that service operator, and specify your desired presentation language if Chinese is not intended.

A.I.G

Vulnerability Patterns
  • 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
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

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 (5)

Vague Triggers

Medium
Category
Not specified by scanner
Confidence
91% confidence
Finding

The trigger condition can activate this skill for generic requests to 'make a PPT' with a compatible service, not just for clearly user-requested use of this specific external endpoint. That creates a risk of routing presentation content to a third-party public service without sufficiently explicit user intent, which is especially concerning because the skill itself acknowledges prompts and uploaded assets may be sent externally.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file repeatedly specifies language: "zh" in API request examples, and the project example also directs creation of a Chinese presentation. The document does not say this is optional, user-selected, or region-specific, which creates a natural-language locale policy concern by steering the skill toward a fixed language without opt-in.

Content

No source excerpt is available for this finding.

External Transmission

Medium
Category
Data Exfiltration
Confidence
60% confidence
Finding

Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.

Content

Scanner excerpt · references/curl-examples.md (reported line 1)May include surrounding context.

md
# Curl Examples

Assume the public deployment:

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
92% confidence
Finding

This markdown file contains curl examples that POST user-provided outline text and generation parameters to a remote API, but the surrounding documentation does not warn that user content is being transmitted off-system. For markdown files, SQP-2 applies when the description omits warnings about behaviors that could affect user data or privacy.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium
Category
Not specified by scanner
Confidence
95% confidence
Finding

Multiple example requests set "language":"zh" in natural-language payloads, which forces a specific language choice in the documented workflow. SQP-3 applies because the file does not present this as optional, user-selected, or justified as a region-specific requirement.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.