abel-strategy-discovery

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

• Third-party content exposure detected (high risk: 0.80). The skill explicitly fetches live, third-party Abel discovery payloads via causal_edge.plugins.abel.discover.discover_graph_payload(...) in narrative_impl.fetch_live_discovery and then reads/consumes discovery.json and readiness outputs (e.g., in prepare_branch) to choose targets, drivers, and to drive warm-cache/evaluation commands, so external/untrusted discovery data can materially influence subsequent tool actions.