Propose a patch

Evidence

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

diff --git a/safety.md b/safety.md
--- a/safety.md
+++ b/safety.md
@@ -109,1 +109,0 @@
-… A flag raised and forgotten gets re-raised as a recommendation next month. **Write in the same turn**: one line in `## Notes` of `~/Clawic/data/nutrition/memory.md` — the date, the signal, what was declined, and what was recommended instead; t…
diff --git a/micronutrients.md b/micronutrients.md
--- a/micronutrients.md
+++ b/micronutrients.md
@@ -115,1 +115,0 @@
-… iodization coverage | **After establishing or revising a nutrient's status**, write its row to `## Nutrient Status` in `~/Clawic/data/nutrition/memory.md` with the intake estimate, the target, the status, and the evidence it rests on…

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: nutrition: 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/nutrition/1.0.2

## Findings with a location
- `safety.md:109` · Instructs the agent to modify its persistent memory or instruction files — safety.md:109 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `micronutrients.md:115` · Instructs the agent to modify its persistent memory or instruction files — micronutrients.md:115 · 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._