fnox-providers

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

• Third-party content exposure detected (high risk: 0.75). The required runtime workflow for this skill is to read fnox.toml and then fetch secrets from configured providers (e.g., AWS/GCP/Azure/Vault/Doppler/1Password/Bitwarden/Infisical); those provider responses are outsider-authored free-form secret values that the agent ingests into the LLM context when it uses the fetched secret text.