Propose a patch

Evidence

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

diff --git a/src/redact.ts b/src/redact.ts
--- a/src/redact.ts
+++ b/src/redact.ts
@@ -32,1 +32,0 @@
-/[\u0000-\u0008\u000B-\u001F\u007F-\u009F​-‏‪-‮⁠-⁤⁦-⁩]|[\u{E0000}-\u{E007F}]/gu;
diff --git a/test/mcp-server.test.ts b/test/mcp-server.test.ts
--- a/test/mcp-server.test.ts
+++ b/test/mcp-server.test.ts
@@ -98,1 +98,0 @@
-const res = await c.callTool({ name: "scan", arguments: { url: "https://user:[email protected]/mcp" } });
diff --git a/test/redact.test.ts b/test/redact.test.ts
--- a/test/redact.test.ts
+++ b/test/redact.test.ts
@@ -21,1 +21,0 @@
-expect(neutralize("p​q")).toBe("p\\u{200b}q");

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.8.0. 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-authprobe: Hidden zero-width characters detected (KillerSkills verdict caution 78)

## 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 78/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/mcp-authprobe/0.8.0

## Findings with a location
- `src/redact.ts:32` · Hidden zero-width characters detected — src/redact.ts:32 · Hidden zero-width characters detected — may conceal content
- `test/mcp-server.test.ts:98` · URL with embedded credentials — test/mcp-server.test.ts:98 · URL with embedded credentials — may be phishing or credential leaking
- `test/redact.test.ts:21` · Hidden zero-width characters detected — test/redact.test.ts:21 · Hidden zero-width characters detected — may conceal content

## Proposed change
The attached patch removes the 3 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._