agent-card-templates

Warn

Audited by Snyk on Feb 16, 2026

Risk Level: MEDIUM
Full Analysis

MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).

  • Third-party content exposure detected (high risk: 0.90). The skill templates and examples (e.g., examples/data-analysis-agent.md and templates/streaming-agent-card.json / templates/multi-capability-agent-card.json) explicitly accept and process arbitrary public URLs such as dataset.sourceUrl, trainingData.sourceUrl, documentUrl, imageUrl, streamSource/sources and webhook/callback URLs, meaning the agent will fetch and interpret untrusted, third‑party content as part of its workflow.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 16, 2026, 01:38 AM