Is claude-api safe to install?

No critical findings, some security notes. 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 dbd4588 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 · anthropics/skills

claude-api: scan report

Reference for the Claude API / Anthropic SDK — model ids, pricing, params, streaming, tool use, MCP, agents, caching, token counting, model migration. TRIGGER — read BEFORE opening the target file; don't skip because… An automated scan of this public skill from anthropics/skills: security, token cost, spec and clarity, with every finding and its fix.

Result

Verdict

claude-api

43/100 · grade F

anthropics/skills/skills/claude-api at dbd4588

Spec 0 · Efficiency 0 · Clarity 20 · Security 23 (each out of 25)

Always loaded 270 tokens · on trigger 25,991 · on demand 45,821

eff/body-tokens warn · SKILL.md~25991 tokens load every time this triggers. Aim for under 5,000; split into reference files read on demand.
eff/body-lines warn · SKILL.mdSKILL.md body is 609 lines; keep it under 500 and move detail into reference files.
spec/description-length warn · SKILL.mddescription is 1068 characters; the limit is 1024 and most agents truncate it.
spec/name-reserved warn · SKILL.mdname contains a reserved word (anthropic, claude).
spec/broken-ref warn · SKILL.md:62References shared/cost-optimization.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:63References shared/evals/build-eval.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:65References shared/evals/eval-hillclimb.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:75References requirements.txt, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:75References setup.py, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:128References shared/tool-use-concepts.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:130References shared/claude-platform-on-aws.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:130References shared/platform-availability.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:176References shared/token-counting.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:198References shared/live-sources.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:200References shared/models.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:204References shared/model-migration.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:213References shared/platform-availability.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:213References shared/model-migration.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:225References shared/model-migration.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:229References shared/models.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:255References shared/model-migration.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:258References shared/model-migration.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:268References shared/model-migration.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:269References shared/model-migration.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:279References shared/live-sources.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:287References shared/prompt-caching.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:293References shared/prompt-caching.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:375References shared/claude-platform-on-aws.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:422References shared/managed-agents-overview.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:430References shared/managed-agents-onboarding.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:431References shared/managed-agents-onboarding-from-quickstart.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:436References shared/managed-agents-onboarding.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:436References shared/managed-agents-onboarding-from-url.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:442References shared/managed-agents-tools.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:442References shared/anthropic-cli.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:444References shared/managed-agents-scheduled-deployments.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:446References shared/managed-agents-multiagent.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:492References shared/admin-api.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:510References tool-use.md, which isn't in the skill folder.
spec/broken-ref warn · SKILL.md:523References shared/model-migration.md, which isn't in the skill folder.
and 55 more.

Where it comes from

Source

Fact	Value
Repository	anthropics/skills
Skill folder	skills/claude-api
Stars	182,098
License	None stated
Commit scanned	dbd4588
Scanned	2026-10-19
Files	25

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 43/100](https://proskills.dev/badge?score=43)](https://proskills.dev/reports/anthropics-claude-api)

Alternatives

Scanned alternatives on ProSkills

Skills in the ProSkills catalog that cover similar ground. Every one passes the same scanner before it ships.

Same repository

More from anthropics/skills

FAQ

Questions

Is claude-api safe to install?: No critical findings, some security notes. 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 dbd4588 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.