Fetching from the wire…
Skills2026-08-03 · source-backed
When an agent consolidates an external observation into long-term memory, attach platform-controlled metadata recording the source's trust level, then gate tool execution by matching action risk against supporting-memory authority. Laundered memories hit a 1.000 attack success rate precisely because the rewrite preserved the trigger and erased the source. You cannot recover provenance at read time.
Each link below shares sources, entities, or timing with this story.
arXiv 2607.29167 describes the mechanism precisely: when an agent consolidates an external observation into long-term memory, the rewrite preserves the action trigger while erasing the low-trust source. The injected instruction resurfaces later looking like user history. Memor...
Li, Huo, and Johnson show that one-way message flow between agents produces neither mimicry nor solo behavior but an entirely novel dynamical state, at identical temperature settings. It's conceptual rather than quantitative, but the implication for orchestrator-worker fan-out...
When authority, resource, and evidence gates run together, a remediation applied by one control changes the action or context another control already judged. The paper's two implemented operators, evidence substitution and resource-budget downroute, do not commute. arXiv Their...
Two thirds. Not two thirds of a contrived jailbreak set. Two thirds of realistic malicious issue requests, against the exact three tools most of the people reading this run daily. Ankur Singh, Jinqiu Yang, and Tse-Hsun Chen built IssueTrojanBench across four attack categories...
Crase (arXiv 2608.24809) is deliberately non-agentic for scholarly search: one search-engine query for seeds, expansion along the 1.5-hop citation neighborhood, pruning of citation edges whose claims lack entailment support, then a recency-aware random walk for ranking. Candid...
Skill files work because they're specific. They name the exact script, the exact API call, the exact flag your repo needs. That specificity is the whole value, and it's also the thing that quietly stops being true the moment the repo tags a new version. Repo2Skill-Evo measured...
MindPattern daily
One email a day at 7 AM. Sources and a take on every story. Unsubscribe anytime.