Propose a patch
A fix the maintainer can act on, with the evidence attached. It opens under your GitHub account in your browser; KillerSkills holds no token and never modifies the package. The fix is verified the only way we verify anything: the next crawl re-runs the new version in the honeypot. 67 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 12 caught lines
Download .patchdiff --git a/SKILL.md b/SKILL.md
--- a/SKILL.md
+++ b/SKILL.md
@@ -75,1 +75,0 @@
-│ memory-write.js → append daily log / MEMORY.md│
@@ -141,1 +140,0 @@
-> **⚠️ Important**: Do NOT instruct memory-flush to write MEMORY.md or run exec commands.
@@ -145,1 +143,0 @@
-### Step 4: Add rules to AGENTS.md
@@ -149,1 +146,0 @@
-(single command: health check + index update + MEMORY.md content)
@@ -271,1 +267,0 @@
-For deeper consolidation (merging semantically similar entries), manually edit MEMORY.md.
diff --git a/scripts/memory-write.js b/scripts/memory-write.js
--- a/scripts/memory-write.js
+++ b/scripts/memory-write.js
@@ -3,1 +3,0 @@
-* memory-write.js v6.0.0 — Write daily logs + MEMORY.md + USER.md + health check
@@ -5,1 +4,0 @@
-* v6.0: MEMORY.md soft cap (5000 chars), USER.md auto-update (1500 chars),
@@ -12,1 +10,0 @@
-* node memory-write.js --snapshot # snapshot MEMORY.md before compaction
@@ -250,1 +247,0 @@
-…&& !coreText && !userText) { console.error('Usage:\n --today "text" [--tag t] Append daily log\n --core "text" [--section s] Append MEMORY.md\n --user "text" Append USER.md\n --snapshot Snapshot MEMORY.md\n --status …
diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -35,1 +35,0 @@
-│ • MEMORY.md integrity │ │ • forces AI to write │
@@ -47,1 +46,0 @@
-│ memory-write.js → daily log + MEMORY.md │
diff --git a/scripts/memory-cron.sh b/scripts/memory-cron.sh
--- a/scripts/memory-cron.sh
+++ b/scripts/memory-cron.sh
@@ -64,1 +64,0 @@
-node "$SCRIPT_DIR/memory-write.js" --workspace "$WORKSPACE" --today "[auto-restore] MEMORY.md restored from snapshot — was wiped to ${CORE_SIZE}B" --tag warning
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 6.0.0. 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-engine-3layer: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 67)
## What the honeypot observed KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.9.2) and scored it **CAUTION 67/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/memory-engine-3layer/6.0.0 ## Findings with a location - `SKILL.md:75` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:75 · Instructs the agent to modify its persistent memory or instruction files - `scripts/memory-write.js:5` · Instructs the agent to modify its persistent memory or instruction files — scripts/memory-write.js:5 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `scripts/memory-write.js:12` · Instructs the agent to modify its persistent memory or instruction files — scripts/memory-write.js:12 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `SKILL.md:149` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:149 · Instructs the agent to modify its persistent memory or instruction files - `scripts/memory-write.js:3` · Instructs the agent to modify its persistent memory or instruction files — scripts/memory-write.js:3 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `README.md:47` · Instructs the agent to modify its persistent memory or instruction files — README.md:47 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `SKILL.md:141` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:141 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:271` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:271 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:145` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:145 · Instructs the agent to modify its persistent memory or instruction files - `scripts/memory-cron.sh:64` · Instructs the agent to modify its persistent memory or instruction files — scripts/memory-cron.sh:64 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `scripts/memory-write.js:250` · Instructs the agent to modify its persistent memory or instruction files — scripts/memory-write.js:250 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `README.md:35` · Instructs the agent to modify its persistent memory or instruction files — README.md:35 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file ## Proposed change The attached patch removes the 12 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._
# or from a terminal, under your own account: gh repo fork openclaw/openclaw --clone && cd openclaw curl -s https://killerskills.ai/skills/clawhub/memory-engine-3layer/6.0.0/patch.diff | git apply --unidiff-zero git checkout -b killerskills/6.0.0 && git commit -am "memory-engine-3layer: Instructs the agent to modify its persistent memory or instruction files" gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/memory-engine-3layer/6.0.0/patch.md)
We count proposals opened, not merged: a merge shows up as a new version that the crawl re-runs. Disputes: the maintainer can contest the verdict from its page; a person reviews it and the outcome is published.