list-templates
Warn
Audited by Snyk on Mar 1, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 1.00). The skill's execution explicitly fetches template files from the public GitHub API (https://api.github.com/repos/tkarakai/ai-agent-instruction-templates/contents/templates) and reads template.yaml descriptions, so untrusted third-party repository content could supply instructions that change agent behavior.
MEDIUM W012: Unverifiable external dependency detected (runtime URL that controls agent).
- Potentially malicious external URL detected (high risk: 0.90). The skill executes a runtime curl to https://api.github.com/repos/tkarakai/ai-agent-instruction-templates/contents/templates?ref=main to fetch repository templates that are AI agent instruction templates (i.e., external content that directly determines available prompts/instructions and is required for the skill), so the URL controls agent instructions at runtime.
Audit Metadata