Is Gzh Design Skill safe?
- Python filesystem read
- 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.
Gzh Design Skill is an agent skill analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators. It can: filesystem read and filesystem write — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).
repo
Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of Gzh Design Skill'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 (2)
The component reads files from disk.
text = open(path, encoding="utf-8", errors="replace").read()
with open(args.file, encoding="utf-8", errors="replace") as f:
content = open(src, encoding="utf-8").read().strip()
tpl = open(tpl_path, encoding="utf-8").read()
Why it matters: Usually legitimate, but worth confirming it can't be steered into reading sensitive files.
Fix: Confirm which files are read and that paths cannot be influenced by untrusted input to reach sensitive locations.
The component writes or deletes files on disk.
with open(os.path.join(img_dir, fname), "wb") as f:
with open(out_md, "w", encoding="utf-8") as f:
open(out, "w", encoding="utf-8").write(out_html)
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.
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 →