Propose a patch

Evidence

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

diff --git a/src/tools/bank.ts b/src/tools/bank.ts
--- a/src/tools/bank.ts
+++ b/src/tools/bank.ts
@@ -59,1 +59,0 @@
-const src = text.replace(/^/, "");
@@ -101,1 +100,0 @@
-const head = text.replace(/^/, "").trimStart().slice(0, 15).toLowerCase();
diff --git a/src/agent/client.ts b/src/agent/client.ts
--- a/src/agent/client.ts
+++ b/src/agent/client.ts
@@ -120,1 +120,0 @@
-const text = body.toString("utf8").replace(/^/, "").trimStart();
diff --git a/src/web.ts b/src/web.ts
--- a/src/web.ts
+++ b/src/web.ts
@@ -236,1 +236,0 @@
-const head = buf.subarray(0, 64).toString("utf8").replace(/^/, "").trimStart().slice(0, 15).toLowerCase();

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.0. 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: szamlazz-mcp: Hidden zero-width characters detected (KillerSkills verdict caution 79)

## 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 79/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/szamlazz-mcp/1.0.0

## Findings with a location
- `src/tools/bank.ts:59` · Hidden zero-width characters detected — src/tools/bank.ts:59 · Hidden zero-width characters detected — may conceal content
- `src/tools/bank.ts:101` · Hidden zero-width characters detected — src/tools/bank.ts:101 · Hidden zero-width characters detected — may conceal content
- `src/agent/client.ts:120` · Hidden zero-width characters detected — src/agent/client.ts:120 · Hidden zero-width characters detected — may conceal content
- `src/web.ts:236` · Hidden zero-width characters detected — src/web.ts:236 · Hidden zero-width characters detected — may conceal content

## 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._