tidas-contract-context

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

• Third-party content exposure detected (high risk: 0.70). The required workflow runs tiangong-lca dataset context-pack / tiangong-lca dataset contract get to fetch contract artifacts, and those CLI outputs (e.g., outputs/ai-context.md, outputs/schema.json, outputs/methodology.yaml, outputs/runtime-ruleset.json) are ingested as readable text into the agent’s LLM context; since the skill does not restrict the source of those contract artifacts to user-authored content, this is an outsider-authored content path (vendor/public dataset content fetched at runtime).