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. 66 · Caution

Evidence

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

Diff · removes 5 caught lines

Download .patch

diff --git a/competitors/triple-memory-skill/SKILL.md b/competitors/triple-memory-skill/SKILL.md
--- a/competitors/triple-memory-skill/SKILL.md
+++ b/competitors/triple-memory-skill/SKILL.md
@@ -86,1 +86,0 @@
-"prompt": "Context is at ~80%. Write session summary to memory/YYYY-MM-DD.md, update MEMORY.md if needed, store key facts to git-notes. Reply NO_REPLY when done."
diff --git a/competitors/elite-longterm-memory/SKILL.md b/competitors/elite-longterm-memory/SKILL.md
--- a/competitors/elite-longterm-memory/SKILL.md
+++ b/competitors/elite-longterm-memory/SKILL.md
@@ -312,1 +312,0 @@
-| Files not loaded | Agent skips reading memory | Add to AGENTS.md rules |
@@ -373,1 +372,0 @@
-| Forgets preferences | Add `## Preferences` section to MEMORY.md |
diff --git a/competitors/triple-memory-skill/references/SETUP.md b/competitors/triple-memory-skill/references/SETUP.md
--- a/competitors/triple-memory-skill/references/SETUP.md
+++ b/competitors/triple-memory-skill/references/SETUP.md
@@ -30,1 +30,0 @@
-Add to your workspace AGENTS.md:
diff --git a/competitors/triple-memory-skill/references/auto-flush-config.json b/competitors/triple-memory-skill/references/auto-flush-config.json
--- a/competitors/triple-memory-skill/references/auto-flush-config.json
+++ b/competitors/triple-memory-skill/references/auto-flush-config.json
@@ -10,1 +10,0 @@
-"prompt": "Context is at ~80%. Write session summary to memory/YYYY-MM-DD.md, update MEMORY.md if needed, store key facts to git-notes. Reply NO_REPLY when done."

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 2.3.5. 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: clawzempic: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 66)

## 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 66/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/clawzempic/2.3.5

## Findings with a location
- `competitors/triple-memory-skill/SKILL.md:86` · Instructs the agent to modify its persistent memory or instruction files — competitors/triple-memory-skill/SKILL.md:86 · Instructs the agent to modify its persistent memory or instruction files
- `competitors/elite-longterm-memory/SKILL.md:312` · Instructs the agent to modify its persistent memory or instruction files — competitors/elite-longterm-memory/SKILL.md:312 · Instructs the agent to modify its persistent memory or instruction files
- `competitors/triple-memory-skill/references/SETUP.md:30` · Instructs the agent to modify its persistent memory or instruction files — competitors/triple-memory-skill/references/SETUP.md:30 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `competitors/elite-longterm-memory/SKILL.md:373` · Instructs the agent to modify its persistent memory or instruction files — competitors/elite-longterm-memory/SKILL.md:373 · Instructs the agent to modify its persistent memory or instruction files
- `competitors/triple-memory-skill/references/auto-flush-config.json:10` · Instructs the agent to modify its persistent memory or instruction files — competitors/triple-memory-skill/references/auto-flush-config.json:10 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## Proposed change
The attached patch removes the 5 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._

Open the issue on GitHub (NextFrontierBuilds/elite-longterm-memory)Fork to open a PR

# or from a terminal, under your own account:
gh repo fork NextFrontierBuilds/elite-longterm-memory --clone && cd elite-longterm-memory
curl -s https://killerskills.ai/skills/clawhub/clawzempic/2.3.5/patch.diff | git apply --unidiff-zero
git checkout -b killerskills/2.3.5 && git commit -am "clawzempic: Instructs the agent to modify its persistent memory or instruction files"
gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/clawzempic/2.3.5/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.