Wget Tool

ReviewAudited by ClawScan on May 12, 2026.

Overview

The downloader purpose is understandable, but the advertised command, install path, and supported features do not match the included code, so it should be reviewed before use.

Review this skill before installing. If you use it, do not assume the documented wget-style options work unless the implementation is fixed, and only download from trusted URLs into safe directories.

Findings (4)

Artifact-based informational review of SKILL.md, metadata, install specs, static scan signals, and capability signals. ClawScan does not execute the skill or run runtime probes.

What this means

A user or agent may rely on advertised safeguards or options that are not actually present, leading to failed downloads or unsafe assumptions about behavior.

Why it was flagged

The included implementation only parses a URL and a fragile `-O` option before calling `urlretrieve`, while SKILL.md advertises resume, recursive mirroring, rate limiting, retries, timeout, headers, and JSON output.

Skill content
if a == '-O': output = sys.argv[i+3]
elif not a.startswith('-'): url = a
...
urllib.request.urlretrieve(url, output or os.path.basename(url))
Recommendation

Align SKILL.md with the actual implementation, or implement and test the advertised options before publishing.

What this means

The agent may fail to run the intended code or may invoke an unexpected local command named `wget-tool` if one exists in the environment.

Why it was flagged

SKILL.md instructs use of a `wget-tool` command, but the artifacts do not install or declare that command and do not clearly connect it to `scripts/wget.py`.

Skill content
No install spec — this is an instruction-only skill.
Recommendation

Provide a clear reviewed entrypoint, declare required binaries, and ensure the documented command maps to the included implementation.

What this means

If used carelessly, it could download untrusted files, overwrite chosen paths, or consume storage/bandwidth.

Why it was flagged

The skill is meant to download web content and write it to local files, including potentially many files when mirroring.

Skill content
-O, --output FILE    Save to specific filename
-r, --recursive      Download recursively
-P, --directory-prefix DIR   Save files under directory
Recommendation

Use only trusted URLs, choose safe output directories, and review downloaded files before opening or executing them.

What this means

Tokens passed on a command line may be exposed through shell history, logs, or process listings, depending on the environment.

Why it was flagged

The documentation encourages passing authentication material in custom HTTP headers, which is expected for private downloads but is sensitive.

Skill content
--header "Authorization: Bearer token123"
...
- **Custom headers** — authentication, API tokens, referrers
Recommendation

Use short-lived, least-privilege tokens and avoid placing real secrets directly in reusable command examples or shared logs.