conventions
Pass
Audited by Gen Agent Trust Hub on Jun 23, 2026
Risk Level: SAFE
Full Analysis
- [EXTERNAL_DOWNLOADS]: The documentation describes installation of the
@anthropic-ai/claude-codepackage from the NPM registry, which is a tool from a well-known service. - [CREDENTIALS_UNSAFE]: Templates utilize standard GitHub Secrets syntax (
${{ secrets.ANTHROPIC_API_KEY }}) for secure credential management in environment variables. - [PROMPT_INJECTION]: The skill includes explicit security constraints in its prompt templates to ensure agents treat issue content as user data rather than instructions, a proactive measure against indirect prompt injection.
- [DATA_EXFILTRATION]: Workflow examples process standard GitHub event metadata (issue titles and bodies) for the intended purpose of automated triage and classification.
Audit Metadata