fastly-cli

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

• Third-party content exposure detected (high risk: 0.90). The skill's required workflows include fetching and interpreting content from arbitrary public sources (e.g., "fastly compute init -f https://github.com/..." in references/compute.md, pre-flight checks like "curl -sI -H 'Host: DESIRED_HOST' https://ORIGIN_ADDRESS/" in references/services.md, and reading DNS/challenge outputs via "fastly tls-subscription describe --include tls_authorizations --json" in references/tls.md), which are untrusted third‑party pages/repos whose responses the agent is expected to read and use to decide subsequent CLI actions.