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. 60 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 5 caught lines
Download .patchdiff --git a/SKILL.md b/SKILL.md --- a/SKILL.md +++ b/SKILL.md @@ -155,1 +155,0 @@ -| User states a **preference** | Write to `MEMORY.md ## Preferences` + `memory_store` (importance=0.9) | @@ -156,1 +155,0 @@ -| User makes a **decision** | Write to `MEMORY.md ## Decisions Log` + Git-Notes | @@ -158,1 +156,0 @@ -| User mentions a **tech stack** | Write to `MEMORY.md ## Projects` | @@ -337,1 +334,0 @@ -1. **Preference detected?** → Write to `SESSION-STATE.md` + append to `MEMORY.md ## Preferences` + `memory_store` (importance=0.9) @@ -338,1 +334,0 @@ -2. **Decision made?** → Write to `SESSION-STATE.md` + append to `MEMORY.md ## Decisions Log` + Git-Notes (SILENTLY)
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.4. 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: liu-longterm-memory: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 60)
## 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 60/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/liu-longterm-memory/1.0.4 ## Findings with a location - `SKILL.md:158` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:158 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:338` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:338 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:337` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:337 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:155` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:155 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:156` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:156 · Instructs the agent to modify its persistent memory or instruction files ## 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._
# or from a terminal, under your own account: gh repo fork louiseliu/liu-longterm-memory --clone && cd liu-longterm-memory curl -s https://killerskills.ai/skills/clawhub/liu-longterm-memory/1.0.4/patch.diff | git apply --unidiff-zero git checkout -b killerskills/1.0.4 && git commit -am "liu-longterm-memory: Instructs the agent to modify its persistent memory or instruction files" gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/liu-longterm-memory/1.0.4/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.