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 8 caught lines
Download .patchdiff --git a/AGENTS.md b/AGENTS.md
--- a/AGENTS.md
+++ b/AGENTS.md
@@ -93,1 +93,0 @@
-4. After every meaningful change: update `.memory.md` + `.achievements.md` + `docs/` + run `shipcheck memory record`.
diff --git a/.achievements.md b/.achievements.md
--- a/.achievements.md
+++ b/.achievements.md
@@ -209,1 +209,0 @@
-- [x] **All install/MCP-add docs updated** to `claude mcp add shipcheck -- uvx shipcheck-mcp` across README, AGENTS.md, DEPLOYMENT.md, website docs
@@ -252,1 +251,0 @@
-7. After every meaningful change: update `.memory.md` + `.achievements.md` + `chat.md`
diff --git a/.memory.md b/.memory.md
--- a/.memory.md
+++ b/.memory.md
@@ -96,1 +96,0 @@
-…rived live from `mcp.list_tools()` so it can't drift again. - **All install/MCP-add instructions updated** across `README.md`, `AGENTS.md`, `docs/DEPLOYMENT.md`, `website/pages/docs/{getting-started,mcp-server}.mdx`, …
@@ -327,1 +326,0 @@
-4. After every meaningful change: update `.memory.md` + `.achievements.md` + `chat.md`
diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md
--- a/CONTRIBUTING.md
+++ b/CONTRIBUTING.md
@@ -30,1 +30,0 @@
-Every meaningful change should update `.memory.md`.
diff --git a/chat.md b/chat.md
--- a/chat.md
+++ b/chat.md
@@ -138,1 +138,0 @@
-7. After every meaningful change: update `.memory.md` + `.achievements.md` + run `shipcheck memory record`
@@ -278,1 +277,0 @@
-#### "Keep updating memory.md and chat.md — do not remove previous content, just append"
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.24.0. 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: shipcheck-mcp: 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: no network, touches nothing outside the project, writes no memory. - See the findings below. Full trace and findings: https://killerskills.ai/skills/pypi/shipcheck-mcp/0.24.0 ## Findings with a location - `AGENTS.md:93` · Instructs the agent to modify its persistent memory or instruction files — AGENTS.md:93 · Instructs the agent to modify its persistent memory or instruction files - `.achievements.md:209` · Instructs the agent to modify its persistent memory or instruction files — .achievements.md:209 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `.achievements.md:252` · Instructs the agent to modify its persistent memory or instruction files — .achievements.md:252 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `.memory.md:96` · Instructs the agent to modify its persistent memory or instruction files — .memory.md:96 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `.memory.md:327` · Instructs the agent to modify its persistent memory or instruction files — .memory.md:327 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `CONTRIBUTING.md:30` · Instructs the agent to modify its persistent memory or instruction files — CONTRIBUTING.md:30 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `chat.md:278` · Instructs the agent to modify its persistent memory or instruction files — chat.md:278 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file - `chat.md:138` · Instructs the agent to modify its persistent memory or instruction files — chat.md:138 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file ## 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._
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.