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 .patchdiff --git a/SKILL.md b/SKILL.md --- a/SKILL.md +++ b/SKILL.md @@ -16,1 +16,0 @@ -- Access to modify `AGENTS.md` in your workspace @@ -32,1 +31,0 @@ -Add the following to your `AGENTS.md`: @@ -132,1 +130,0 @@ -Modify the importance detection in AGENTS.md: @@ -298,1 +295,0 @@ -# Remove from AGENTS.md (manual edit) diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -63,1 +63,0 @@ -Add to your `AGENTS.md` | 添加到你的AGENTS.md:
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.0. 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: conversation-guard: 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 1.9.2) 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/conversation-guard/0.1.0 ## Findings with a location - `SKILL.md:132` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:132 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:16` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:16 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:298` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:298 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:32` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:32 · Instructs the agent to modify its persistent memory or instruction files - `README.md:63` · Instructs the agent to modify its persistent memory or instruction files — README.md:63 · 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._
# or from a terminal, under your own account: gh repo fork zfanmy/dreammoon-conversation-guard --clone && cd dreammoon-conversation-guard curl -s https://killerskills.ai/skills/clawhub/conversation-guard/0.1.0/patch.diff | git apply --unidiff-zero git checkout -b killerskills/0.1.0 && git commit -am "conversation-guard: Instructs the agent to modify its persistent memory or instruction files" gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/conversation-guard/0.1.0/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.