Propose a patch

Evidence

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

diff --git a/loyalty.md b/loyalty.md
--- a/loyalty.md
+++ b/loyalty.md
@@ -87,1 +87,0 @@
-…oined, tier earned, points credited or spent, benefit discovered or fee paid**, write it in the same turn: the row in `## Loyalty` in `memory.md` (or `programs.md` once split), every expiry into `## Due`, card benefits into …
diff --git a/wishlist.md b/wishlist.md
--- a/wishlist.md
+++ b/wishlist.md
@@ -74,1 +74,0 @@
-…es a place file in `artifacts/` **After adding, ranking or killing an entry**, write it in the same turn: the row in `## Wishlist` in `memory.md` (or `destinations.md` once it has split), and in `## Due` both any release dat…

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.2. 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: travel: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 72)

## 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 72/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/travel/1.0.2

## Findings with a location
- `loyalty.md:87` · Instructs the agent to modify its persistent memory or instruction files — loyalty.md:87 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `wishlist.md:74` · Instructs the agent to modify its persistent memory or instruction files — wishlist.md:74 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## 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._