Reported observations below are attributed to the linked sources. Review questions and controls are editorial interpretation.
What the source reports
SkillJack evaluates poisoned experience becoming persistent reusable skills in two skill-evolution systems. The authors test behavior after removing the source records.
Primary records: S15 ↗
The trust boundary
Transient task history was promoted into reusable procedural authority.
What this does not establish
This is an experimental paper, not an observed attack against an identified organization. Its systems, trajectories, and scoring bound the conclusion.
We reviewed the linked publication text or cataloged evidence level. We did not execute the suspect package, independently reproduce the investigation, or verify current registry availability.
Questions for a review
These are practical questions prompted by the case, not controls independently validated by this website.
- Lineage
- Which source experiences produced the extracted skill revision?
- Condition retention
- Does the reusable procedure preserve the original task’s data, recipient, and authorization conditions?
- Revocation
- Are source-record deletion and derived-skill removal tested separately?
Editorial lesson
Preserve artifact lineage and test removal of derived skills separately from deletion of source context.
For your own environment, turn the question into a bounded test with an exact package identity, synthetic input, expected permitted behavior, prohibited effect, and observable stopping point. Keep a blocked attempt distinct from a completed effect. Preserve the legitimate task result alongside the security observation.