← knowledgebasemcp@0.1.0

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. 76 · Caution

Evidence

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

Diff · removes 4 caught lines

Download .patch
diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -14,1 +14,0 @@
---8<-- [start:run]
@@ -60,1 +59,0 @@
---8<-- [end:run]
diff --git a/test_KnowledgeBaseMCP.py b/test_KnowledgeBaseMCP.py
--- a/test_KnowledgeBaseMCP.py
+++ b/test_KnowledgeBaseMCP.py
@@ -581,1 +581,0 @@
-g("remote", "add", "origin", "https://user:[email protected]/o/r.git")
@@ -652,1 +651,0 @@
-g("remote", "set-url", "origin", "https://user:[email protected]/o/r.git")

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: knowledgebasemcp: HTML comment carrying imperative instructions to the agent (KillerSkills verdict caution 76)

## 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 76/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/knowledgebasemcp/0.1.0

## Findings with a location
- `README.md:14` · HTML comment carrying imperative instructions to the agent — README.md:14 · HTML comment carrying imperative instructions to the agent
- `README.md:60` · HTML comment carrying imperative instructions to the agent — README.md:60 · HTML comment carrying imperative instructions to the agent
- `test_KnowledgeBaseMCP.py:581` · URL with embedded credentials — test_KnowledgeBaseMCP.py:581 · URL with embedded credentials — may be phishing or credential leaking
- `test_KnowledgeBaseMCP.py:652` · URL with embedded credentials — test_KnowledgeBaseMCP.py:652 · URL with embedded credentials — may be phishing or credential leaking

## 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 dfoulks1/KnowledgeBaseMCP --clone && cd KnowledgeBaseMCP
curl -s https://killerskills.ai/skills/glama/knowledgebasemcp/0.1.0/patch.diff | git apply --unidiff-zero
git checkout -b killerskills/0.1.0 && git commit -am "knowledgebasemcp: HTML comment carrying imperative instructions to the agent"
gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/glama/knowledgebasemcp/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.