terraform-stacks

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

• Third-party content exposure detected (medium risk: 0.65). The required runtime workflow described in SKILL.md (monitoring via HCP Terraform API) can fetch outsider-authored free text from deployment failure diagnostics (attributes.detail, attributes.summary, and attributes.diags[].snippet.code) and/or plan/apply artifacts, which would then be ingested into the agent’s LLM context if the agent summarizes or reasons over those fields.