Is offensive-initial-access safe to install?

3 critical findings: read before installing. The scan covers prompt injection, hidden Unicode, remote code execution and credential access in every text file of the skill. It cannot judge intent, so read any flagged line in context before installing.

How was this score calculated?

Four checks of 25 points each: spec, efficiency, clarity and security. Findings take points off the check they belong to, and any critical finding caps the grade at F. The same scanner runs in your browser at proskills.dev/scan.

Is this report current?

It was made from commit a8de813 on 2026-10-19. If the skill has changed since, paste the new version into the scanner for a fresh score.

I wrote this skill. Can I fix the score or have the page removed?

Fix the findings and push. The reports are rebuilt from GitHub on a schedule, so the next run picks the change up. To have the page removed, open an issue on the ProSkills GitHub repo.

Scan reports · SnailSploit/Claude-Red

offensive-initial-access: scan report

An automated scan of this public skill from SnailSploit/Claude-Red: security, token cost, spec and clarity, with every finding and its fix.

Result

Verdict

offensive-initial-access

25/100 · grade F

SnailSploit/Claude-Red/Skills/infrastructure/offensive-initial-access at a8de813

Spec 0 · Efficiency 5 · Clarity 20 · Security 0 (each out of 25)

Always loaded 1 tokens · on trigger 16,348 · on demand 0

spec/frontmatter critical · SKILL.md:1SKILL.md must start with YAML frontmatter (--- name, description ---).
sec/remote-exec critical · SKILL.md:71Downloads and executes remote code.
sec/fake-prerequisite critical · SKILL.md:940Tells the user or agent to fetch and run a binary, the pattern behind the ClawHavoc malware campaign.
eff/body-tokens warn · SKILL.md~16348 tokens load every time this triggers. Aim for under 5,000; split into reference files read on demand.
sec/persistence warn · SKILL.md:388Installs persistence or edits shell/agent config.
sec/hidden-comment warn · SKILL.mdHTML comment carries instructions the user won't see rendered.
eff/body-lines warn · SKILL.mdSKILL.md body is 1527 lines; keep it under 500 and move detail into reference files.
sec/prompt-injection warn · SKILL.md:846Tries to override the agent's instructions. Reads as an example or a warning here; check it in context.
spec/broken-ref warn · SKILL.md:258References exploit/edr.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:262References exploit/edr.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:754References exploit/shellcode.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:797References exploit/edr.md, which isn't in the skill folder.
clarity/vague info · SKILL.md13 vague phrases (consider , etc, best practices). Replace with concrete thresholds.
sec/plain-http info · SKILL.mdLinks over plain http.

Where it comes from

Source

Fact	Value
Repository	SnailSploit/Claude-Red
Skill folder	Skills/infrastructure/offensive-initial-access
Stars	7,608
License	MIT
Commit scanned	a8de813
Scanned	2026-10-19
Files	1

ProSkills doesn't host or redistribute this skill. Get it from its repository, and check the license before reusing it. Something wrong here? Open an issue for a rescan or removal.

For maintainers

Badge for the README

If you maintain this skill, this badge shows its score and links to this report. Fix findings and the score moves with the next scan.

[![ProSkills scan 25/100](https://proskills.dev/badge?score=25)](https://proskills.dev/reports/snailsploit-offensive-initial-access)

Same repository

More from SnailSploit/Claude-Red

FAQ

Questions

Is offensive-initial-access safe to install?: 3 critical findings: read before installing. The scan covers prompt injection, hidden Unicode, remote code execution and credential access in every text file of the skill. It cannot judge intent, so read any flagged line in context before installing.
How was this score calculated?: Four checks of 25 points each: spec, efficiency, clarity and security. Findings take points off the check they belong to, and any critical finding caps the grade at F. The same scanner runs in your browser at proskills.dev/scan.
Is this report current?: It was made from commit a8de813 on 2026-10-19. If the skill has changed since, paste the new version into the scanner for a fresh score.
I wrote this skill. Can I fix the score or have the page removed?: Fix the findings and push. The reports are rebuilt from GitHub on a schedule, so the next run picks the change up. To have the page removed, open an issue on the ProSkills GitHub repo.

Keep reading

Free tool

Scan your own skill

Paste a SKILL.md or drop a folder. It is scored in your browser and nothing is uploaded.

Open the Skill Scanner

Want a skill that already passes? Start with a free one.