truefoundry-helm

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 instructs the agent to discover and read Helm chart metadata/values from public, user-maintained sources (e.g., Artifact Hub pages, chart repositories, and via helm CLI commands like "helm show values") as part of manifest construction (see "Finding & Sourcing Helm Charts" in SKILL.md and references/helm-chart-sources.md), which exposes the agent to untrusted third‑party content that can influence actions.