ppt-produce-bycodex

• Outcome: Review
• Latest audit: Jun 3, 2026, 2:44 AM
• Version:
  1.0.0

Overview

The skill is mostly a disclosed PPT-generation workflow, but it asks the agent to source a personal shell startup file to use API credentials, which is broader than necessary.

Review this skill before installing if you do not want agents reading or sourcing your shell configuration. Prefer providing OPENAI_API_KEY and OPENAI_BASE_URL through a scoped runtime environment, verify the configured API endpoint, and only allow the optional frontend demo/dev-server workflow when you explicitly need it.

SkillSpector

By NVIDIA

Vulnerability Patterns

• Data Exfiltration: External Transmission, Env Variable Harvesting, File System Enumeration
• Excessive Agency: Unrestricted Tool Access, Autonomous Decision Making, Scope Creep
• Prompt Injection: Instruction Override, Hidden Instructions, Exfiltration Commands
• Privilege Escalation: Excessive Permissions, Sudo/Root Execution, Credential Access
• Supply Chain: Unpinned Dependencies, External Script Fetching, Obfuscated Code

Findings (4)

Context-Inappropriate Capability

Low

• Confidence: 86% confidence
• Finding: The skill instructs the agent to read `~/.zshrc` to obtain `OPENAI_API_KEY` and `OPENAI_BASE_URL`, which unnecessarily reaches into user shell configuration and may expose secrets unrelated to the task. Pulling credentials from dotfiles broadens access beyond the project workspace and can leak, misuse, or normalize secret harvesting behavior in a content-production skill.

Context-Inappropriate Capability

Medium

• Confidence: 94% confidence
• Finding: The guide instructs the agent to source ~/.zshrc, inspect whether OPENAI_API_KEY is present, print OPENAI_BASE_URL, and call the configured API endpoint. For a PPT-generation skill, touching shell startup files and probing credential/configuration state exceeds the minimum needed scope and can expose sensitive environment details or normalize unnecessary secret-adjacent inspection.

Context-Inappropriate Capability

High

• Confidence: 97% confidence
• Finding: The guide expands from PPT/PNG/PPTX production into building local frontend demos, invoking other design/frontend skills, and potentially starting a dev server. This is a material capability expansion beyond the declared skill purpose, increasing the chance of arbitrary code generation/execution, package installation, local service exposure, and workspace pollution under the guise of presentation work.

Missing User Warnings

Medium

• Confidence: 90% confidence
• Finding: Reading API-related environment settings from shell configuration without an explicit user-facing warning creates a real secret-handling risk. In this context, the danger is heightened because the skill is for PPT generation, so accessing personal shell config is not an obvious or minimally necessary step and may violate least-privilege expectations.

VirusTotal

65/65 vendors flagged this skill as clean.