Security audit

md-to-nanobanana-ppt

Security checks for vulnerabilities and agentic risk

Overview

This skill is a disclosed Chinese Markdown-to-PPT workflow that uses external image generation and delivery tools in ways that fit its stated purpose.

Before installing, confirm that Chinese-language slide text is acceptable and avoid using highly sensitive reports unless you are comfortable sending their contents to the configured image-generation, Feishu, and email integrations.

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

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
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep

Findings (1)

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The instructions require that all text rendered in generated images must be in Chinese characters, and later restate this as a mandatory rule. This is a natural-language locale constraint applied by default, with no user opt-in or documented region-specific justification, which matches the policy-violation criteria.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.