← mcp-acedatacloud@2026.11.3.0

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. 71 · Caution

Evidence

The sandbox observed nothing beyond the static findings; the proposal cites those.

Diff · removes 8 caught lines

Download .patch
diff --git a/vscode/README.md b/vscode/README.md
--- a/vscode/README.md
+++ b/vscode/README.md
@@ -32,1 +32,0 @@
-BEGIN TOKEN ONBOARDING
@@ -37,1 +36,0 @@
-END TOKEN ONBOARDING
diff --git a/jetbrains/README.md b/jetbrains/README.md
--- a/jetbrains/README.md
+++ b/jetbrains/README.md
@@ -23,1 +23,0 @@
-BEGIN TOKEN ONBOARDING
@@ -28,1 +27,0 @@
-END TOKEN ONBOARDING
diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -581,1 +581,0 @@
-BEGIN TOKEN ONBOARDING
@@ -586,1 +585,0 @@
-END TOKEN ONBOARDING
diff --git a/README.pypi.md b/README.pypi.md
--- a/README.pypi.md
+++ b/README.pypi.md
@@ -582,1 +582,0 @@
-BEGIN TOKEN ONBOARDING
@@ -587,1 +586,0 @@
-END TOKEN ONBOARDING

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 2026.11.3.0. 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: mcp-acedatacloud: HTML comment carrying imperative instructions to the agent (KillerSkills verdict caution 71)

## What the honeypot observed
KillerSkills ran **[email protected]** in an isolated sandbox (decoy credentials, recording proxy, syscall trace; engine 1.7) and scored it **CAUTION 71/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/mcp-acedatacloud/2026.11.3.0

## Findings with a location
- `vscode/README.md:32` · HTML comment carrying imperative instructions to the agent — vscode/README.md:32 · HTML comment carrying imperative instructions to the agent
- `vscode/README.md:37` · HTML comment carrying imperative instructions to the agent — vscode/README.md:37 · HTML comment carrying imperative instructions to the agent
- `jetbrains/README.md:23` · HTML comment carrying imperative instructions to the agent — jetbrains/README.md:23 · HTML comment carrying imperative instructions to the agent
- `README.md:581` · HTML comment carrying imperative instructions to the agent — README.md:581 · HTML comment carrying imperative instructions to the agent
- `jetbrains/README.md:28` · HTML comment carrying imperative instructions to the agent — jetbrains/README.md:28 · HTML comment carrying imperative instructions to the agent
- `README.pypi.md:587` · HTML comment carrying imperative instructions to the agent — README.pypi.md:587 · HTML comment carrying imperative instructions to the agent
- `README.pypi.md:582` · HTML comment carrying imperative instructions to the agent — README.pypi.md:582 · HTML comment carrying imperative instructions to the agent
- `README.md:586` · HTML comment carrying imperative instructions to the agent — README.md:586 · HTML comment carrying imperative instructions to the agent

## 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._
Open the issue on GitHub (AceDataCloud/AceDataCloudMCP)Fork to open a PR
# or from a terminal, under your own account:
gh repo fork AceDataCloud/AceDataCloudMCP --clone && cd AceDataCloudMCP
curl -s https://killerskills.ai/skills/pypi/mcp-acedatacloud/2026.11.3.0/patch.diff | git apply --unidiff-zero
git checkout -b killerskills/2026.11.3.0 && git commit -am "mcp-acedatacloud: HTML comment carrying imperative instructions to the agent"
gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/pypi/mcp-acedatacloud/2026.11.3.0/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.