Security audit

bitsoul ppt 制作器

Security checks for vulnerabilities and agentic risk

Overview

This is a simple presentation-generation skill with disclosed styling instructions and no local code execution, persistence, credential access, or hidden behavior.

Install only if you want Chinese, minimalist tech-style PPT/HTML output. Review generated presentations before sharing, especially any external CDN links, and prefer pinned HTTPS resources or bundled assets for sensitive content.

A.I.G

Vulnerability Patterns

Insecure DependenciesIntroduces malicious components through unsafe dependency sources
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)

T08 · Insecure Dependencies

Warning

Location: SKILL.md:58
Finding: Unpinned Runtime Dependencies from Unspecified CDN Sources
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (3)

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 94% confidence
Finding: The description says the skill should activate whenever the user needs to generate a PPT, which is a broad trigger without clear scope boundaries. Overly general activation conditions can cause the skill to engage in contexts where the user did not explicitly request this specific presentation format, increasing the chance of inappropriate routing, unwanted style enforcement, or interference with other safer/more suitable skills.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill metadata and body require Chinese-language output and a specific Chinese presentation style without indicating that user language preference should take precedence. This can cause user-intent mismatch, accessibility problems, and incorrect behavior for multilingual or non-Chinese users, though it is primarily a quality and safety issue rather than a direct security exploit.
Content: No source excerpt is available for this finding.

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The body text repeats the one-click generation behavior in similarly broad terms, reinforcing a vague trigger model rather than constraining use. This can make the skill over-apply itself to loosely related requests and reduce user control over when stylized transformation of content occurs.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.