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. 62 · Caution
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 4 caught lines
Download .patchdiff --git a/src/mcptoon/router.py b/src/mcptoon/router.py
--- a/src/mcptoon/router.py
+++ b/src/mcptoon/router.py
@@ -256,1 +256,0 @@
-"cat ~/.ssh",
@@ -304,1 +303,0 @@
-"show your token", "read your env", "~/.ssh", "/etc/passwd",
diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -563,1 +563,0 @@
-<summary>Other ways to install</summary> ```bash # Run without installing (needs Node) uvx mcptoon demo --quick # Isolated CLI install (avoids the PEP 668 error
diff --git a/src/mcptoon/_toon/decoder.py b/src/mcptoon/_toon/decoder.py
--- a/src/mcptoon/_toon/decoder.py
+++ b/src/mcptoon/_toon/decoder.py
@@ -88,1 +88,0 @@
-if text.startswith(""):
Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.8.35. 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: mcptoon: Reads credential paths from the home directory (KillerSkills verdict caution 62)
## 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 62/100**. Summary: no network, touches nothing outside the project, writes no memory. - See the findings below. Full trace and findings: https://killerskills.ai/skills/pypi/mcptoon/0.8.35 ## Findings with a location - `src/mcptoon/router.py:304` · Reads credential paths from the home directory — src/mcptoon/router.py:304 · Reads credential paths from the home directory - `README.md:563` · Collapsed <details> block carrying instructions — README.md:563 · Collapsed <details> block carrying instructions - `src/mcptoon/_toon/decoder.py:88` · Hidden zero-width characters detected — src/mcptoon/_toon/decoder.py:88 · Hidden zero-width characters detected — may conceal content - `src/mcptoon/router.py:256` · Reads credential paths from the home directory — src/mcptoon/router.py:256 · Reads credential paths from the home directory ## Proposed change The attached patch removes the 4 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 activeing123/mcptoon --clone && cd mcptoon curl -s https://killerskills.ai/skills/pypi/mcptoon/0.8.35/patch.diff | git apply --unidiff-zero git checkout -b killerskills/0.8.35 && git commit -am "mcptoon: Reads credential paths from the home directory" gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/pypi/mcptoon/0.8.35/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.