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
@@ -52,1 +52,0 @@
-Do not compose your response yet. First write the entry to MEMORY.md in the appropriate section (`## User`, `## Knowledge`, `## Rules`, etc.):
@@ -58,1 +57,0 @@
-If the content is detailed (multi-step procedure, analysis, etc.), create a project workspace instead and add a pointer to MEMORY.md.
@@ -96,1 +94,0 @@
-- Unfinished items: add to MEMORY.md `## In Progress` as `- [ ] {task} | from:YYYY-MM-DD` (skip if already tracked).
@@ -129,1 +126,0 @@
-3. Add a one-line pointer to MEMORY.md `## Projects`:
@@ -164,1 +160,0 @@
-When a MEMORY.md entry is disputed: look up `from:YYYY-MM-DD`, use `memory_search` or read the daily file to find the original context. If wrong or stale, update MEMORY.md and log the correction.
diff --git a/references/init.md b/references/init.md
--- a/references/init.md
+++ b/references/init.md
@@ -17,1 +17,0 @@
-6. Write restructured MEMORY.md
diff --git a/references/promote-compact.md b/references/promote-compact.md
--- a/references/promote-compact.md
+++ b/references/promote-compact.md
@@ -25,1 +25,0 @@
-| Contradicts existing MEMORY.md entry | Promote newer, update/remove old |
@@ -76,1 +75,0 @@
-3. Write cleaned MEMORY.md
diff --git a/references/workspace-init.md b/references/workspace-init.md
--- a/references/workspace-init.md
+++ b/references/workspace-init.md
@@ -26,1 +26,0 @@
-5. Add pointer to MEMORY.md `## Projects`:
@@ -36,1 +35,0 @@
-5. Add pointer to MEMORY.md `## Projects`
@@ -43,1 +41,0 @@
-3. Add pointer to MEMORY.md `## Projects`:

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: memory-lifecycle: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 71)

## 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 71/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/memory-lifecycle/1.0.0

## Findings with a location
- `SKILL.md:164` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:164 · Instructs the agent to modify its persistent memory or instruction files
- `SKILL.md:129` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:129 · Instructs the agent to modify its persistent memory or instruction files
- `SKILL.md:96` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:96 · Instructs the agent to modify its persistent memory or instruction files
- `SKILL.md:58` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:58 · Instructs the agent to modify its persistent memory or instruction files
- `SKILL.md:52` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:52 · Instructs the agent to modify its persistent memory or instruction files
- `references/init.md:17` · Instructs the agent to modify its persistent memory or instruction files — references/init.md:17 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `references/promote-compact.md:76` · Instructs the agent to modify its persistent memory or instruction files — references/promote-compact.md:76 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `references/workspace-init.md:26` · Instructs the agent to modify its persistent memory or instruction files — references/workspace-init.md:26 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `references/promote-compact.md:25` · Instructs the agent to modify its persistent memory or instruction files — references/promote-compact.md:25 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `references/workspace-init.md:43` · Instructs the agent to modify its persistent memory or instruction files — references/workspace-init.md:43 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `references/workspace-init.md:36` · Instructs the agent to modify its persistent memory or instruction files — references/workspace-init.md:36 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## Proposed change
The attached patch removes the 11 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._