Security audit

PDF To PPTX

Security checks for vulnerabilities and agentic risk

Overview

The skill is a straightforward PDF-to-PowerPoint upload API, but users should treat uploaded PDFs as leaving their device for third-party processing.

Install only if you are comfortable sending PDFs to the third-party service listed in the skill. Avoid confidential, regulated, or legally sensitive documents unless you have separately verified the provider's privacy, retention, deletion, and download-link access controls.

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
MCP Tool PoisoningHidden Instructions, Unicode Deception, Parameter Description Injection
Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access

Findings (6)

Description-Behavior Mismatch

High

Category: Not specified by scanner
Confidence: 98% confidence
Finding: The skill metadata promises conversion of PDFs into editable PowerPoint presentations, but the OpenAPI spec exposes only a raw PDF upload endpoint and does not define any PowerPoint-generation, status, or output-download operation. This mismatch can mislead users and downstream agents into sending sensitive files to a service whose actual behavior is opaque, increasing the risk of unauthorized retention, repurposing, or deceptive data collection.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 96% confidence
Finding: The skill instructs users to upload raw PDF content to a third-party API but does not warn that documents may contain sensitive or regulated data. This omission can lead users to transmit confidential business, personal, or legal information externally without understanding the privacy, retention, or compliance implications.
Content: No source excerpt is available for this finding.

External Transmission

Medium

Category: Data Exfiltration
Confidence: 91% confidence
Finding: The sample response exposes that converted files are hosted and retrieved from an external URL, confirming that uploaded document content leaves the local environment and is stored or made accessible on a remote service. If users process sensitive PDFs, this creates confidentiality and data-governance risk, especially if file URLs are guessable, retained too long, or shared unintentionally.
Content: Scanner excerpt · SKILL.md (reported line 35)May include surrounding context.
"output_file": "document_converted.pptx", "pages_processed": 12, "conversion_time_ms": 2450, "file_url": "https://api.mkkpro.com/files/abc123def456/document_converted.pptx" }

text

External Transmission

Medium

Category: Data Exfiltration
Confidence: 50% 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 · SKILL.md (reported line 118)May include surrounding context.
md
## References - **Kong Route:** `https://api.mkkpro.com/creative/pdf-to-pptx` - **API Docs:** `https://api.mkkpro.com:8001/docs`

Vague Triggers

Medium

Category: Not specified by scanner
Confidence: 84% confidence
Finding: The API exposes a generic file-upload action with no scope limitations, trigger constraints, or guidance on when the action should or should not be invoked. In an agent skill context, ambiguous upload actions are risky because they can cause over-broad activation and unnecessary transfer of user documents, including sensitive PDFs, without clear task boundaries.
Content: No source excerpt is available for this finding.

Natural-Language Policy Violations

Low

Category: Not specified by scanner
Confidence: 7% confidence
Finding: SQP-3 only covers natural-language language or locale policy violations. This file does not force a language or locale, so there is no substantive policy issue here.
Content: No source excerpt is available for this finding.

Static analysis

No suspicious patterns detected.