fix(skills): harden slash skill activation across chat channels (#3466)

* support slash skill activation

* format slash skill activation

* Preserve slash skill activation with uploads

* Address slash skill review feedback

* Address slash skill follow-up review

* Fix lazy slash skill storage resolution

* Keep slash skill activation out of system prompt

* Address slash skill review issues

* fix: harden slash skill command handling

* feat(frontend): add slash skill autocomplete

* fix: address slash skill review feedback

* fix: preserve slash skill text for IM uploads
This commit is contained in:
DanielWalnut
2026-06-09 23:07:17 +08:00
committed by GitHub
parent 18bbb82f07
commit 16391e35ab
31 changed files with 2758 additions and 57 deletions
@@ -260,6 +260,22 @@ describe("formatThreadAsJSON", () => {
expect(raw).toContain("real user text");
});
it("strips <slash_skill_activation> as defence in depth", () => {
// Slash activation normally rides in a hidden HumanMessage. If a replay
// or state merge loses the flag, export must still not leak full SKILL.md
// content into a user-visible transcript.
const leaky = human("real user task", {
id: "leak-slash-skill",
content:
"<slash_skill_activation>\n<skill_content># Secret SKILL.md\nUse internal source.</skill_content>\n</slash_skill_activation>\nreal user task",
} as unknown as Partial<Message>);
const raw = formatThreadAsJSON(makeThread(), [leaky]);
expect(raw).not.toContain("<slash_skill_activation>");
expect(raw).not.toContain("Secret SKILL.md");
expect(raw).not.toContain("internal source");
expect(raw).toContain("real user task");
});
it("sanitises tool message content when includeToolMessages is true", () => {
const message = {
id: "t-leak",