multi-agent-performance-profiling
Warn
Audited by Snyk on Feb 28, 2026
Risk Level: MEDIUM
Full Analysis
MEDIUM W011: Third-party content exposure detected (indirect prompt injection risk).
- Third-party content exposure detected (high risk: 0.80). The skill's required workflow (SKILL.md) and the profiling template (references/profiling_template.py) explicitly call out downloading and ingesting external data (e.g., download_from_cdn(url), CloudFront downloads) and then parse/analyze those files to drive profiling and prioritization, so untrusted third‑party content is fetched and can materially influence the agent's decisions.
Audit Metadata