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 8 caught lines
Download .patchdiff --git a/SKILL.md b/SKILL.md --- a/SKILL.md +++ b/SKILL.md @@ -67,1 +67,0 @@ -| `read`/`write`/`edit` | File operations | MEMORY.md, active-tasks.json | @@ -75,1 +74,0 @@ -| `acpx prompt -s <session> "<instruction>"` | Send prompt (creates session if new, appends if existing) | @@ -111,1 +109,0 @@ -- **User → Agent**: `acpx prompt -s <session> "<instruction>"` enters the prompt queue @@ -183,1 +180,0 @@ -5. Write MEMORY.md task entry (see §7) @@ -279,1 +275,0 @@ -4. Update MEMORY.md: status=completed, add PR link @@ -297,1 +292,0 @@ -Edit MEMORY.md: status → abandoned or completed @@ -341,1 +335,0 @@ -| `failed` | Update MEMORY.md → notify user of failure reason | diff --git a/scripts/launch.sh b/scripts/launch.sh --- a/scripts/launch.sh +++ b/scripts/launch.sh @@ -228,1 +228,0 @@ -# Update MEMORY.md
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.1. 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: conduxt: 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/conduxt/1.0.1 ## Findings with a location - `SKILL.md:67` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:67 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:75` · Fake instruction boundary tag — SKILL.md:75 · Fake instruction boundary tag - `SKILL.md:111` · Fake instruction boundary tag — SKILL.md:111 · Fake instruction boundary tag - `SKILL.md:279` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:279 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:341` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:341 · Instructs the agent to modify its persistent memory or instruction files - `scripts/launch.sh:228` · Instructs the agent to modify its persistent memory or instruction files — scripts/launch.sh:228 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `SKILL.md:297` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:297 · Instructs the agent to modify its persistent memory or instruction files - `SKILL.md:183` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:183 · Instructs the agent to modify its persistent memory or instruction files ## Proposed change The attached patch removes the 8 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 xuezhouyang/conduxt --clone && cd conduxt curl -s https://killerskills.ai/skills/clawhub/conduxt/1.0.1/patch.diff | git apply --unidiff-zero git checkout -b killerskills/1.0.1 && git commit -am "conduxt: Instructs the agent to modify its persistent memory or instruction files" gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/conduxt/1.0.1/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.