Propose a patch

Evidence

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

diff --git a/SKILL.md b/SKILL.md
--- a/SKILL.md
+++ b/SKILL.md
@@ -275,1 +275,0 @@
-| Wake | `wake <id> <prompt> [--wait SECS] [--dry-run] [--signer] [--key] [--json]` | `compute_wake {machine, prompt, wait? 0–120}` | `wake_machine {machine, prompt ≤ 8000, waitMs? 0–15000}` — scope `
@@ -294,1 +293,0 @@
-wake <machine> <prompt> [--wait SECS] [--dry-run] [--signer NAME] [--key PATH] [--json]

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.0. 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: kax-compute: Fake instruction boundary tag (KillerSkills verdict caution 67)

## 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 67/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/kax-compute/1.0.0

## Findings with a location
- `SKILL.md:275` · Fake instruction boundary tag — SKILL.md:275 · Fake instruction boundary tag
- `SKILL.md:294` · Fake instruction boundary tag — SKILL.md:294 · Fake instruction boundary tag

## 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._