speed-loop
Warn
Audited by Snyk on Feb 26, 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's required startup instructions (see references/start.txt referenced in SKILL.md and Getting Started) explicitly tell the agent to "Conduct web research on optimizing data systems," which requires fetching and interpreting open/public web content that could be untrusted and influence the agent's decisions and actions.
Audit Metadata