flux

Warn

Audited by Snyk on Feb 19, 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 explicitly instructs fetching and validating content from public/untrusted sources — e.g., SKILL.md's "Check Git/Registry" step and TROUBLESHOOTING-WORKFLOWS.md (commands like git clone, kubectl apply -k git+https://..., flux create source git --url=...) which require reading Git repositories, Helm/OCI registries, and container registries as part of the workflow, exposing the agent to untrusted third-party content.
Audit Metadata
Risk Level
MEDIUM
Analyzed
Feb 19, 2026, 12:32 PM