Back to skill

Security audit

MagicSlides: AI Presentation Maker (PPTX & PDF)

Security checks for vulnerabilities and agentic risk

Overview

This skill coherently uses MagicSlides to create and edit presentations, with expected cloud processing and optional local API-key storage.

Use source material you are permitted to send to MagicSlides, especially when documents contain confidential figures or personal information. Protect any saved API key and keep the default endpoint unless you trust the replacement. Check your requested language and review generated content before sharing.

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
  • Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
  • Output HandlingUnvalidated Output Injection, Cross-Context Output, Unbounded Output
  • MCP Least PrivilegeUnderdeclared Capability, Wildcard Permission, Missing Permission Declaration
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Findings (9)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 46)May include surrounding context.

md
node scripts/magicslides.mjs whoami # check the key works

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 47)May include surrounding context.

md
node scripts/magicslides.mjs <tool> '<json args>' # call any tool

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 48)May include surrounding context.

md
node scripts/magicslides.mjs <tool> @args.json # args from a file (use for big decks)

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 49)May include surrounding context.

md
node scripts/magicslides.mjs tools # list every tool + arguments

Incomplete referenced artifact analysis

High
Category
analysis-evasion
Confidence
100% confidence
Finding

Referenced artifact was not completely inspected

Content

Scanner excerpt · SKILL.md (reported line 54)May include surrounding context.

md
`node scripts/magicslides.mjs login ms-api-...` (in `~/.config/magicslides/api-key`).

Skill declares no tool scope ('permissions' or 'allowed-tools') but code capabilities were detected: env, network.

Medium
Category
MCP Least Privilege
Confidence
70% confidence
Finding

Without declared permissions the skill's intent is opaque and cannot be validated.

Content

No source excerpt is available for this finding.

Unrestricted Tool Access

Medium
Category
Excessive Agency
Confidence
80% confidence
Finding

Skill grants unrestricted tool access without appropriate constraints. An agent with unfettered tool access can perform arbitrary actions including file modification, network requests, and code execution.

Content

Scanner excerpt · SKILL.md (reported line 47)May include surrounding context.

bash
node scripts/magicslides.mjs whoami                       # check the key works
node scripts/magicslides.mjs <tool> '<json args>'         # call any tool
node scripts/magicslides.mjs <tool> @args.json            # args from a file (use for big decks)
node scripts/magicslides.mjs tools                        # list every tool + arguments

The non-slot generation path hard-codes English without user opt-in.

Medium
Category
Output Handling
Confidence
91% confidence
Finding

This workflow explicitly supplies "language": "en" when calling create_presentation, regardless of the user's language or preference. The later instruction to use the user's language does not resolve this conflicting, path-specific English setting.

Content

No source excerpt is available for this finding.

The source-to-slides workflow sends user-provided content to MagicSlides without a privacy warning.

Medium
Category
Output Handling
Confidence
96% confidence
Finding

The workflow directs the agent to extract material from user documents and send derived content to an external service without a privacy checkpoint. Although MagicSlides is openly identified as the provider, a request to convert a document does not necessarily establish informed authorization to disclose confidential figures, personal information, or proprietary text to that provider.

Content

No source excerpt is available for this finding.