SkillTotal

Is Karpathy Llm Wiki safe?

No malicious indicators - review capabilities before installing
Notable — review in context (capabilities are not malware):
  • Python filesystem read

repo is an AI agent_skill analyzed by SkillTotal's deterministic static scanner. The scan found no malicious indicators, though 1 risky construct are reported for review. It can: filesystem read — capabilities are what the code can do, not a verdict on intent. Risk score 0/100 (low).

repo

agent_skill · https://github.com/Astro-Han/karpathy-llm-wiki
LOW
0
/ 100 risk score
Snapshot · scanned Aug 5, 2026 · repo@eafcc77 · engine 0.38.1 / ruleset 42

Automated static-analysis result. It can contain false positives and false negatives, and is not a claim about the intent of Karpathy Llm Wiki's authors. Report a false positive.

Capabilities — what this component can do (not a risk score):
filesystem read

Behavioral traits

How this component maps to the CSA agentic threat model. Descriptive — it never affects the risk score.

Filesystem reach
Tool Execution Context

Findings (1)

MEDIUMPython filesystem readST-FS-PY-READ

The component reads files from disk.

document = parse_document(path.read_text(encoding="utf-8"))
text = article.read_text(encoding="utf-8")
text = strip_fences(log_file.read_text(encoding="utf-8"))
for link in raw_links_of(article.read_text(encoding="utf-8")):

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.

Check your own component

Run the same evidence-backed scan on any MCP server, agent skill, or package.

Scan your own component

How we determine this: deterministic static analysis (regex + AST), evidence-anchored, no code execution. Methodology →