reference-claude-api
Pass
Audited by Gen Agent Trust Hub on May 12, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill consists entirely of documentation files (.md) designed for reference. It contains no executable scripts, configuration files (like package.json or requirements.txt), or automated tasks that could perform malicious actions.
- [EXTERNAL_DOWNLOADS]: The skill links to official Anthropic documentation (platform.claude.com) and references official API endpoints (api.anthropic.com). These are trusted, well-known service domains and do not constitute a security risk.
- [CREDENTIALS_UNSAFE]: No hardcoded API keys or sensitive credentials were found. Documentation examples correctly use environment variable placeholders such as
$ANTHROPIC_API_KEY. - [PROMPT_INJECTION]: The content is purely instructional and technical. No patterns attempting to override agent behavior, bypass safety filters, or extract system prompts were detected.
Audit Metadata