Security audit

Ppt Task Orchestrator

Security checks for vulnerabilities and agentic risk

Overview

This skill mostly matches its PPT-to-image delivery purpose, but it needs Review because its delivery settings can write outside the intended folder and may include more generated images than requested.

Review this skill before installing if you handle untrusted PPTX files or request JSON. Use dry-run first, keep delivery.outputDir inside a known safe folder, use a simple ZIP filename with no slashes or traversal, and expect OCR processing plus temporary local copies of slide images.

A.I.G

Vulnerability Patterns

Insecure Skill Coding PracticesFinds exploitable flaws such as hardcoded secrets or command injection
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)

T09 · Insecure Skill Coding Practices

Error

Location: lib/delivery.js:35
Finding: Arbitrary File Overwrite Through Unsanitized Delivery ZIP Path
Content: View full analysis
Remediation: View remediation

SkillSpector

Vulnerability Patterns

Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
Excessive AgencyUnrestricted Tool Access, Autonomous Decision Making, Scope Creep
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 (4)

Intent-Code Divergence

Medium

Category: Not specified by scanner
Confidence: 95% confidence
Finding: The code ignores the configured copySelectedOnly behavior and always iterates over all exported PNG paths, which can cause unintended files to be copied into the delivery directory and bundled ZIP. In this orchestration context, that can leak extra generated assets, drafts, or alternate artboards beyond what the caller expected to distribute, creating an information disclosure and over-delivery risk.
Content: No source excerpt is available for this finding.

Context-Inappropriate Capability

Medium

Category: Not specified by scanner
Confidence: 90% confidence
Finding: The manifest describes production orchestration for PPTX page task extraction and batch image delivery by reusing other skills. In this file, the skill spawns local executables (tesseract and swift running Vision OCR) to analyze extracted slide images, which is a materially broader capability than plain PPTX parsing and is not explicitly justified by the stated purpose.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 91% confidence
Finding: The code invokes external executables ("tesseract" and "swift") to process slide images, which is subprocess execution on user data. Although the function names and comments describe the implementation, there is no user-facing warning, prompt, or visible logging indicating that external OCR tools will be run.
Content: No source excerpt is available for this finding.

Missing User Warnings

Medium

Category: Not specified by scanner
Confidence: 87% confidence
Finding: The parser creates a temporary directory and writes extracted slide media files to it, which is a file-write operation involving user-provided presentation content. In this file there is no confirmation prompt, user-facing log/print, or comment disclosing that slide images will be materialized on local disk for OCR processing.
Content: No source excerpt is available for this finding.

Static analysis

Detected: suspicious.dangerous_exec

Shell command execution detected (child_process).

Critical

Code: suspicious.dangerous_exec
Location: lib/ppt-parser.js:497