Is Frontend Slides safe?
What Frontend Slides does
Frontend Slides is a coding-agent skill for creating HTML presentations from scratch or by converting PowerPoint files; it generates visual style previews for you to choose from. It is published in the zarazhangrui/frontend-slides repository and packaged as a Claude Code plugin. It needs filesystem and shell access: it writes HTML files and ships helper scripts to extract PPTX content, export PDF, and deploy a deck to Vercel. Before installing, note that scripts/deploy.sh publishes a deck to a permanent, shareable URL; run it only for slides you intend to share outside your machine.
- Python filesystem write/delete
What to do: Nothing here argues against installing it. Grant the capabilities it lists only if you expect the tool to need them.
Frontend Slides is an agent skill analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators. It can: filesystem write — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).
frontend-slides
Get notified when this component changes
Change alerts aren't live yet. Leave your email and we'll let you know when they launch. We use it only for this and delete it on request.
Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of Frontend Slides's authors. Report a false positive.
Behavioral traits
How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.
Findings (1)
The component writes or deletes files on disk.
with open(image_path, "wb") as f:
with open(output_path, "w") as f:
with open(image_path, "wb") as f:
with open(output_path, "w") as f:
Why it matters: Usually legitimate, but worth confirming the paths can't be controlled by untrusted input.
Fix: Confirm which files are written/deleted and that paths cannot be influenced by untrusted input.
Maintain Frontend Slides?
The free Claude Code plugin scans each npm, PyPI or MCP package with this report's open-source engine before the install command runs. It runs on your machine and needs no account.
Check your own component
Run the same evidence-backed scan on any MCP server, agent skill, or package.
Scan your own componentHow we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →