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. 78 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 11 caught lines
Download .patchdiff --git a/AGENTS.md b/AGENTS.md --- a/AGENTS.md +++ b/AGENTS.md @@ -31,1 +31,0 @@ -- You can **read, edit, and update** MEMORY.md freely in main sessions @@ -34,1 +33,0 @@ -- Over time, review your daily files and update MEMORY.md with what's worth keeping @@ -40,1 +38,0 @@ -- When you learn a lesson → update AGENTS.md, TOOLS.md, or the relevant skill @@ -176,1 +173,0 @@ -- **Review and update MEMORY.md** (see below) @@ -182,1 +178,0 @@ -3. Update `MEMORY.md` with distilled learnings diff --git a/context-memory.md b/context-memory.md --- a/context-memory.md +++ b/context-memory.md @@ -231,1 +231,0 @@ -- **Lesson Learning**: When you learn a lesson → update AGENTS.md, TOOLS.md, or skill @@ -239,1 +238,0 @@ -3. **Update MEMORY.md**: Update `MEMORY.md` with distilled learnings @@ -371,1 +369,0 @@ -2. **Review Regularly**: Update MEMORY.md from daily files diff --git a/MEMORY.md b/MEMORY.md --- a/MEMORY.md +++ b/MEMORY.md @@ -132,1 +132,0 @@ -- ✅ MEMORY.md - Complete update with all systems (this file) diff --git a/system-prompt.md b/system-prompt.md --- a/system-prompt.md +++ b/system-prompt.md @@ -275,1 +275,0 @@ -- Review and update MEMORY.md diff --git a/workspace-management.md b/workspace-management.md --- a/workspace-management.md +++ b/workspace-management.md @@ -190,1 +190,0 @@ -git add AGENTS.md SOUL.md TOOLS.md IDENTITY.md USER.md HEARTBEAT.md memory/
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: clawdbot-knowledge: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 78)
## 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 78/100**. Summary: no network, touches nothing outside the project, writes no memory. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/clawdbot-knowledge/1.0.0 ## Findings with a location - `AGENTS.md:40` · Instructs the agent to modify its persistent memory or instruction files — AGENTS.md:40 · Instructs the agent to modify its persistent memory or instruction files - `context-memory.md:371` · Instructs the agent to modify its persistent memory or instruction files — context-memory.md:371 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `AGENTS.md:176` · Instructs the agent to modify its persistent memory or instruction files — AGENTS.md:176 · Instructs the agent to modify its persistent memory or instruction files - `AGENTS.md:34` · Instructs the agent to modify its persistent memory or instruction files — AGENTS.md:34 · Instructs the agent to modify its persistent memory or instruction files - `AGENTS.md:182` · Instructs the agent to modify its persistent memory or instruction files — AGENTS.md:182 · Instructs the agent to modify its persistent memory or instruction files - `MEMORY.md:132` · Instructs the agent to modify its persistent memory or instruction files — MEMORY.md:132 · Instructs the agent to modify its persistent memory or instruction files - `AGENTS.md:31` · Instructs the agent to modify its persistent memory or instruction files — AGENTS.md:31 · Instructs the agent to modify its persistent memory or instruction files - `context-memory.md:239` · Instructs the agent to modify its persistent memory or instruction files — context-memory.md:239 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `context-memory.md:231` · Instructs the agent to modify its persistent memory or instruction files — context-memory.md:231 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `system-prompt.md:275` · Instructs the agent to modify its persistent memory or instruction files — system-prompt.md:275 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `workspace-management.md:190` · Instructs the agent to modify its persistent memory or instruction files — workspace-management.md:190 · 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._
# or from a terminal, under your own account: gh repo fork QuantGeekDev/mcp-framework --clone && cd mcp-framework curl -s https://killerskills.ai/skills/clawhub/clawdbot-knowledge/1.0.0/patch.diff | git apply --unidiff-zero git checkout -b killerskills/1.0.0 && git commit -am "clawdbot-knowledge: Instructs the agent to modify its persistent memory or instruction files" gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/clawdbot-knowledge/1.0.0/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.