Is terminal-bench-loop safe to install?

No known risky patterns found. 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 2cc7992 on 2026-10-16. 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 · paperclipai/paperclip

terminal-bench-loop: scan report

Run one Terminal-Bench task through a bounded Paperclip smoke/diagnosis/fix loop. Use when asked to drive Terminal-Bench until it passes, rerun a Terminal-Bench loop, or iterate with board-gated fixes and diagnosis. An automated scan of this public skill from paperclipai/paperclip: security, token cost, spec and clarity, with every finding and its fix.

Verdict

No known risky patterns found

Nothing in the skill matched the scanner's security rules: no instruction overrides, hidden characters, remote code or credential access.

terminal-bench-loopScan 86/100Grade B

paperclipai/paperclip/.agents/skills/terminal-bench-loop at 2cc7992

Spec 17 · Efficiency 19 · Clarity 25 · Security 25 (each out of 25)

Always loaded 59 tokens · on trigger 6,205 · on demand 0

eff/body-tokens warn · SKILL.md~6205 tokens load every time this triggers. Aim for under 5,000; split into reference files read on demand.
spec/broken-ref warn · SKILL.md:15References doc/execution-semantics.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:74References doc/execution-semantics.md, which isn't in the skill folder.

Source

Fact	Value
Repository	paperclipai/paperclip
Skill folder	.agents/skills/terminal-bench-loop
Stars	103,099
License	MIT
Commit scanned	2cc7992
Scanned	2026-10-16
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.

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 86/100](https://proskills.dev/badge?score=86)](https://proskills.dev/reports/paperclipai-terminal-bench-loop)

More from paperclipai/paperclip

Skill	Scan	Grade
add-product-e2e-eval	78/100	C
add-runner-eval	86/100	B
check-pr	93/100	A
company-creator	96/100	A
create-agent-adapter	80/100	B
create-external-bot-integration	95/100	A
create-issue-interaction-ui	97/100	A
create-paperclip-bundled-skill	84/100	B
create-verification-skill	81/100	B
deal-with-security-advisory	100/100	A
delegate-work	83/100	B
design-guide	96/100	A

Questions

Is terminal-bench-loop safe to install?: No known risky patterns found. 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 2cc7992 on 2026-10-16. 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

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.