# Resource-scan receipt: anthropics/skills — skill-creator SKILL.md

A resource-scan receipt is the record of one static check run over one public AI resource — a repository, a gist, a skill file, a script, an MCP server package or a config — at the public URL named on the receipt. The receipt binds to the exact bytes scanned, named by their SHA-256 hash, and is sealed into the public ledger like every other record here. Each receipt carries the published check list with the outcome of every check and the findings in plain language. The analysis is static only: the bytes are read as text and are never executed, installed or run, and nothing is fetched from behind a login. A receipt publishes evidence, never a judgment: the summary line counts how many of the checks flagged, and the reader draws their own conclusion from the findings. Re-scanning the same URL creates a new receipt; the artifact page shows the latest receipt and the history, and when the bytes at a URL change the new receipt is a new version — no receipt is ever edited or overwritten.

Artifact: anthropics/skills — skill-creator SKILL.md
Canonical URL: https://raw.githubusercontent.com/anthropics/skills/main/skills/skill-creator/SKILL.md
Fetched from: https://raw.githubusercontent.com/anthropics/skills/main/skills/skill-creator/SKILL.md
SHA-256 of the exact bytes scanned: dcd4803e61e913e6fc27294184cd3a71f09f5e924ff20c8a9a20173e7b3c2bcf
Bytes scanned: 33168 · Scanned: 2026-10-27T12:24:02.908Z · Scanner: resource-scan-v1
Summary: 3 of 8 checks flagged (evidence only — the findings below are the record)
Analysis: static only — the bytes were read as text and were never executed, installed or run.
Ledger entry: 1626

## Checks (latest receipt)

### Outbound network references — pass

No outbound network references — no URLs, domains or network calls — were found in the scanned bytes.

### Credential and environment access — pass

No credential or environment access patterns were found in the scanned bytes.

### Install and postinstall hooks — pass

No install or postinstall hooks were found in the scanned bytes.

### Obfuscation and encoded payloads — pass

No obfuscation or encoded-payload signs were found in the scanned bytes.

### Shell-outs and download-and-execute — flag

The scanned bytes contain shell-out or download patterns: shell invocation from Python (subprocess, os.system, Popen). Code that runs shell commands acts with the full permissions of whoever runs it.

Evidence: shell invocation from Python (subprocess, os.system, Popen)

### Permission declarations vs behavior — flag

The bytes show filesystem behavior, and no permissions declaration was found in the scanned bytes to compare it against.

Evidence: behavior: filesystem

### Known-bad indicators — flag

The scanned bytes match these known-bad indicators from the scanner's published pattern list: token- or credential-taking vocabulary (stealer, grabber, exfiltrate). Each match is a reproducible pattern match on the bytes named by the hash; re-running the published check on the same bytes reaches the same finding.

Evidence: token- or credential-taking vocabulary (stealer, grabber, exfiltrate)

### Provenance facts (weak signals) — pass

Provenance facts, labeled weak signals — they say where the bytes sit, not what the bytes do: source host: raw.githubusercontent.com; repository: anthropics/skills; bytes scanned: 33168.

Evidence: source host: raw.githubusercontent.com; repository: anthropics/skills; bytes scanned: 33168

## History (1 receipt, 1 version)

Every receipt for this artifact so far names the same SHA-256: the bytes have not changed between scans.

- 2026-10-27 — 3 of 8 checks flagged · SHA-256 dcd4803e61e913e6… · 33168 bytes · scanner resource-scan-v1 · ledger entry 1626

Machine form: https://www.rightshold.com/v1/resource-scans/raw-githubusercontent-com-anthropics-skills-main-skills-379c2e076a