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
@@ -89,1 +89,0 @@
-…** Saving, merging a duplicate, promoting a variant, and retiring a recipe each write their row: `index.md` for the entry, `made/<year>.md` for the cook, `memory.md` `## Boxes` for any new file. Retirement means the row moves to `## Retired` in…
diff --git a/capture.md b/capture.md
--- a/capture.md
+++ b/capture.md
@@ -64,1 +64,0 @@
-… Rule 1 and 9). If the capture revealed a source worth trusting or distrusting, add its row to `## Sources` in `~/Clawic/data/recipe/memory.md`. Formats and thresholds: `memory-template.md`. 
diff --git a/memory-template.md b/memory-template.md
--- a/memory-template.md
+++ b/memory-template.md
@@ -346,1 +346,0 @@
-…Read the file before adding. If the same allergy or condition is already there, update that line in place — never append a second one, and never restate it in `memory.md`. - **Allergy ≠ intolerance ≠ chosen diet.** An allergy or a condition goes her…

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: recipe: 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/recipe/1.0.2

## Findings with a location
- `SKILL.md:89` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:89 · Instructs the agent to modify its persistent memory or instruction files
- `capture.md:64` · Instructs the agent to modify its persistent memory or instruction files — capture.md:64 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `memory-template.md:346` · Instructs the agent to modify its persistent memory or instruction files — memory-template.md:346 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## Proposed change
The attached patch removes the 3 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._