Propose a patch

Evidence

The sandbox observed nothing beyond the static findings; the proposal cites those.

diff --git a/skills/ai-engine/SKILL.md b/skills/ai-engine/SKILL.md
--- a/skills/ai-engine/SKILL.md
+++ b/skills/ai-engine/SKILL.md
@@ -155,1 +155,0 @@
-…nse、登录/API Key、付费订阅、供应商配额或并发保护。 - 管理中转权益复用 Managed `platform-ai-account`：先 `GetRelayTokenAccount({TargetUserId})`，再 `SetRelayTokenLimit({TargetUserId,IsUnlimited,Expecte…
diff --git a/skills/microi.v8.js b/skills/microi.v8.js
--- a/skills/microi.v8.js
+++ b/skills/microi.v8.js
@@ -717,1 +717,0 @@
-// Do not pass secrets, arbitrary URLs or a caller-selected storage endpoint.

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 6.3.0. If the behavior is intended, declare it (host under permissions.network, a line in the README) instead of removing it; the next crawl scores declarations.

Issue / PR body

Title: cli: Credential pass-through configuration (KillerSkills verdict caution 68)

## What the honeypot observed
KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.8.1) and scored it **CAUTION 68/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/npm/cli/6.3.0

## Findings with a location
- `skills/ai-engine/SKILL.md:155` · Credential pass-through configuration — skills/ai-engine/SKILL.md:155 · Credential pass-through configuration — agent relays sensitive credentials
- `skills/microi.v8.js:717` · Credential pass-through configuration — skills/microi.v8.js:717 · Credential pass-through configuration — agent relays sensitive credentials

## Proposed change
The attached patch removes the 2 lines above. If the behavior is intended, the fix is to declare it instead: list the host under `permissions.network` (or the MCP manifest) and say in the README why the package needs it; the next crawl will re-score it with the declaration taken into account.

## How this will be verified
Nothing is "verified safe" by assertion. When a new version is published, KillerSkills re-runs it in the honeypot and the verdict page updates; you can trigger it early from the verdict page ("Re-scan after I publish a fix"). Reply here or at [email protected] if you believe the verdict is wrong; disputes are reviewed by a person and the outcome is published on the verdict page.

_Proposed through killerskills.ai/threats by a user of the package, under their own GitHub account. The evidence is public; the package was never modified by KillerSkills._