Propose a patch

Evidence

• Contacted install.meilisearch.com: not declared and not needed for the documented job.

diff --git a/SKILL.md b/SKILL.md
--- a/SKILL.md
+++ b/SKILL.md
@@ -22,1 +22,0 @@
-- **Write**: MeiliSearch indexes (`core`, `working`, `archive`), `MEMORY.md` (distillation only with `--apply`)
@@ -80,1 +79,0 @@
-bash scripts/distill.sh --apply        # Actually write to MEMORY.md
diff --git a/scripts/distill.sh b/scripts/distill.sh
--- a/scripts/distill.sh
+++ b/scripts/distill.sh
@@ -2,1 +2,0 @@
-# Memory distillation: extract key facts from daily notes and append to MEMORY.md
@@ -6,1 +5,0 @@
-# Default is dry-run. Use --apply to actually write to MEMORY.md.
@@ -200,1 +198,0 @@
-print("\nRun with --apply to write these to MEMORY.md")
diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -17,1 +17,0 @@
-- **Write**: MeiliSearch indexes (`core`, `working`, `archive`), `MEMORY.md` (distillation only with `--apply`)
@@ -51,1 +50,0 @@
-bash scripts/distill.sh --apply        # Write to MEMORY.md
diff --git a/skill-card.md b/skill-card.md
--- a/skill-card.md
+++ b/skill-card.md
@@ -54,1 +54,0 @@
-**Other Properties Related to Output:** [Can update MeiliSearch indexes and append distilled facts to MEMORY.md when explicitly applied.]

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 3.0.0. 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: meili-memory: Contacted install.meilisearch.com: not declared and not needed for the documented job (KillerSkills verdict blocked 46)

## 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 **BLOCKED 46/100**. Summary: sends data to install.meilisearch.com.

- Contacted install.meilisearch.com: not declared and not needed for the documented job.

Full trace and findings: https://killerskills.ai/skills/clawhub/meili-memory/3.0.0

## Findings with a location
- `SKILL.md:22` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:22 · Instructs the agent to modify its persistent memory or instruction files
- `SKILL.md:80` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:80 · Instructs the agent to modify its persistent memory or instruction files
- `scripts/distill.sh:6` · Instructs the agent to modify its persistent memory or instruction files — scripts/distill.sh:6 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `README.md:17` · Instructs the agent to modify its persistent memory or instruction files — README.md:17 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `README.md:51` · Instructs the agent to modify its persistent memory or instruction files — README.md:51 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `skill-card.md:54` · Instructs the agent to modify its persistent memory or instruction files — skill-card.md:54 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `scripts/distill.sh:200` · Instructs the agent to modify its persistent memory or instruction files — scripts/distill.sh:200 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `scripts/distill.sh:2` · Instructs the agent to modify its persistent memory or instruction files — scripts/distill.sh:2 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## Proposed change
The attached patch removes the 8 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._