← code-context-mcp@0.0.12

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. 66 · 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
@@ -41,1 +41,0 @@
-<summary><strong>1. OpenAI Configuration (Default)</strong></summary> OpenAI provides high-quality embeddings with excellent performance for code understanding.
@@ -70,1 +69,0 @@
-<summary><strong>2. VoyageAI Configuration</strong></summary> VoyageAI offers specialized code embeddings optimized for programming languages. ```bash # Require
@@ -96,1 +94,0 @@
-<summary><strong>3. Gemini Configuration</strong></summary> Google's Gemini provides competitive embeddings with good multilingual support. ```bash # Required: 
@@ -120,1 +117,0 @@
-<summary><strong>4. Ollama Configuration (Local/Self-hosted)</strong></summary> Ollama allows you to run embeddings locally without sending data to external ser

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.0.12. 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: code-context-mcp: Collapsed <details> block carrying instructions (KillerSkills verdict caution 66)

## 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 66/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/npm/code-context-mcp/0.0.12

## Findings with a location
- `README.md:96` · Collapsed <details> block carrying instructions — README.md:96 · Collapsed <details> block carrying instructions
- `README.md:70` · Collapsed <details> block carrying instructions — README.md:70 · Collapsed <details> block carrying instructions
- `README.md:120` · Collapsed <details> block carrying instructions — README.md:120 · Collapsed <details> block carrying instructions
- `README.md:41` · Collapsed <details> block carrying instructions — README.md:41 · Collapsed <details> block carrying instructions

## 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 zilliztech/code-context --clone && cd code-context
curl -s https://killerskills.ai/skills/npm/code-context-mcp/0.0.12/patch.diff | git apply --unidiff-zero
git checkout -b killerskills/0.0.12 && git commit -am "code-context-mcp: Collapsed <details> block carrying instructions"
gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/npm/code-context-mcp/0.0.12/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.