SR
SKILLRADAR
AI Security • Benchmarking • Index
Menu⌄
Trust Report v1

claude-api

|- 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 it "looks like a one-liner" — whenever: the prompt names Cla

Overall
60
Trust
29
Utility
88
Momentum
82

Install caution

High-risk behavior present

Risk: High

Source: Anthropic Skills

Path: skills/claude-api/SKILL.md

Review flags: browser/session access, credential or secret references, filesystem/home-directory access, network access or external URLs. These are review signals, not definitive security judgments; inspect before installing.

Required permissions

  • • Environment variables / secrets
  • • Shell commands
  • • Network/API usage
  • • Filesystem/home access
  • • Browser/session access

Permissions are inferred from SKILL.md text only. They are review prompts, not guarantees about runtime behavior.

Risk flags explained

browser_or_session_accessmedium

Mentions browser automation, cookies, sessions, local storage, or browser state.

credential_or_secret_referencehigh

Mentions tokens, API keys, passwords, or private-key style environment variables.

filesystem_write_or_home_accessmedium

Mentions filesystem writes, deletes, home-directory paths, or config/key locations.

network_accessmedium

Mentions external URLs, network APIs, downloads, or HTTP client usage.

shell_commandmedium

Contains shell command snippets. Review commands before copy/paste or agent execution.

Score explanation

Trust

  • • Trust starts at 90 before review-signal penalties and metadata bonuses.
  • • Risk-signal penalty: -63 from 5 detected flag(s).
  • • Metadata bonus: +2 from author/version/description fields.

Utility

  • • Utility starts at 55 and rewards clear descriptions, runnable examples, and explicit setup needs.
  • • Description present: yes.
  • • Command examples detected: 8.
  • • Environment variables detected: 5.

Momentum

  • • Momentum starts at 45 and uses public repo activity signals.
  • • Recent repo update within 13 days.
  • • Recent commit volume: 3 commit(s) in the lookback window (+9).
  • • Source has strong public adoption: 166866 stars.
  • • Fork activity suggests reuse: 19880 forks.

Overall

  • • Overall score weights trust 45%, utility 35%, and momentum 20%.

Detected signals

Env vars

  • • ANTHROPIC_API_KEY
  • • ANTHROPIC_AUTH_TOKEN
  • • ANTHROPIC_IDENTITY_TOKEN
  • • ANTHROPIC_IDENTITY_TOKEN_FILE
  • • API

Commands

  • • — converting a curl from an API key is a header change, not a key swap). Always pass
  • • curl
  • • curl/
  • • curl/examples.md
  • • curl/managed-agents.md
  • • python-docx
  • • python-pptx
  • • python/

URLs

  • • https://aws.amazon.com/bedrock/pricing/
  • • https://cloud.google.com/vertex-ai/generative-ai/pricing#claude-models

Provenance & evidence

SkillRadar makes each review traceable back to the exact source path, source blob SHA, scanner version, and text-only policy that produced the report.

source
github.com/anthropics/skills@main
path
skills/claude-api/SKILL.md
source blob SHA
6ddbf0b48d0a55a3065ae870556c9d77fc310a58
scanner version
0.3.0
security model
text_only_no_execute_no_install_no_secrets
scan policy
Fetched and scored as text only; no install, no execution, no runtime loading.

Evidence snippets

credential_or_secret_reference

…ce and capability-filter examples. --- ## Authentication (Quick Reference) **An unset `ANTHROPIC_API_KEY` does NOT mean there are no credentials.** The SDKs and the `ant` CLI resolve credentials…

filesystem_write_or_home_access

…tory access fails** (network restricted, timeouts, clone blocked): do not keep retrying — write code from the patterns and namespace/package tables in the `{lang}/` file, run the compil…

network_access

…). This is the default whenever a supported SDK exists for the project. 2. **Raw HTTP** (`curl`, `requests`, `fetch`, `httpx`, etc.) — only when the user explicitly asks for cURL/REST/…

browser_or_session_access

…ng multi-turn agent with file mounts | Agent | **Managed Agents** | Per-session containers, SSE event stream, Skills + MCP | | Agent that runs on a schedule (cron,…

shell_command

….). This is the default whenever a supported SDK exists for the project. 2. **Raw HTTP** (`curl`, `requests`, `fetch`, `httpx`, etc.) — only when the user explicitly asks for cURL/REST/r…

Watch this skill

Get alerted when this skill adds credential requirements, shell commands, external domains, remote installer patterns, or risk-level changes.

Join watchlist beta

Methodology note

SkillRadar scans SKILL.md as hostile text only. It does not execute commands, install packages, or load third-party skills.

View source SKILL.mdBack to changesView sources