Back to skill

Security audit

Birthday PPT Creator

Security checks for vulnerabilities and agentic risk

Overview

This skill is a straightforward birthday PowerPoint generator that reads user-selected photos and writes a presentation file without hidden persistence or credential access.

Install only if a Chinese-language birthday PPT generator is what you want. Use local photo files, review the generated presentation before sharing because it contains child photos and birth-date details, and choose an output filename that will not replace something important.

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
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 (2)

Missing User Warnings

Medium
Category
Not specified by scanner
Confidence
93% confidence
Finding

The skill explicitly allows photos to be provided as remote URLs, but it does not warn that fetching those URLs causes network access and may disclose user/system metadata such as IP address, timing, and possibly access patterns to third parties. In an agent context, silent remote retrieval also increases SSRF-style risk if internal or sensitive URLs are accepted as 'photos' without restriction.

Content

No source excerpt is available for this finding.

Natural-Language Policy Violations

Low
Category
Not specified by scanner
Confidence
93% confidence
Finding

The module docstring presents the skill name and usage instructions exclusively in Chinese, and the CLI help text later follows the same pattern. This can violate a language/locale policy when a skill forces a specific language without user opt-in or justification.

Content

No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.