Propose a patch

Evidence

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

diff --git a/lib/token-store.js b/lib/token-store.js
--- a/lib/token-store.js
+++ b/lib/token-store.js
@@ -930,1 +930,0 @@
-"Enter the token manually, or set SLACK_TOKEN and SLACK_COOKIE in the environment.",
diff --git a/scripts/token-cli.js b/scripts/token-cli.js
--- a/scripts/token-cli.js
+++ b/scripts/token-cli.js
@@ -153,1 +153,0 @@
-console.log("Or enter the token by hand: npx -y @jtalk22/slack-mcp --setup");
diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -67,1 +67,0 @@
-<summary><strong>Side by side: the managed integration path vs. the local session path</strong></summary> <br> | | Slack official MCP | **Slack MCP Server — loc
@@ -259,1 +258,0 @@
-<summary><strong>Author labels on every message</strong></summary> Each message carries `origin` (`self`, `internal`, `external`, `bot`, `unknown`) and `author_
@@ -281,1 +279,0 @@
-<summary><strong>Read-only mode, for when a label is not enough</strong></summary> ```bash npx -y @jtalk22/slack-mcp --read-only # or SLACK_MCP_READ_ONLY=1 ``` 
diff --git a/lib/skills.js b/lib/skills.js
--- a/lib/skills.js
+++ b/lib/skills.js
@@ -270,1 +270,0 @@
-const FRONTMATTER = /^?---[ \t]*\r?\n[\s\S]*?\r?\n---[ \t]*(?:\r?\n|$)/;

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 5.2.1. 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: slack-mcp: Prompting user to enter sensitive credentials (KillerSkills verdict caution 64)

## 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 64/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/npm/slack-mcp/5.2.1

## Findings with a location
- `lib/token-store.js:930` · Prompting user to enter sensitive credentials — lib/token-store.js:930 · Prompting user to enter sensitive credentials — social engineering
- `scripts/token-cli.js:153` · Prompting user to enter sensitive credentials — scripts/token-cli.js:153 · Prompting user to enter sensitive credentials — social engineering
- `README.md:259` · Collapsed <details> block carrying instructions — README.md:259 · Collapsed <details> block carrying instructions
- `README.md:281` · Collapsed <details> block carrying instructions — README.md:281 · Collapsed <details> block carrying instructions
- `lib/skills.js:270` · Hidden zero-width characters detected — lib/skills.js:270 · Hidden zero-width characters detected — may conceal content
- `README.md:67` · Collapsed <details> block carrying instructions — README.md:67 · Collapsed <details> block carrying instructions

## Proposed change
The attached patch removes the 6 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._