Propose a patch

Evidence

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

diff --git a/.claude-plugin/plugin.json b/.claude-plugin/plugin.json
--- a/.claude-plugin/plugin.json
+++ b/.claude-plugin/plugin.json
@@ -18,1 +18,0 @@
-"title": "Relay token",
diff --git a/server.json b/server.json
--- a/server.json
+++ b/server.json
@@ -20,1 +20,0 @@
-{ "name": "PALAVER_TOKEN", "description": "Shared or per-member relay token", "isRequired": true, "isSecret": true, "format": "string" },

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.1. 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: hoptell: Credential pass-through configuration (KillerSkills verdict caution 61)

## 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 61/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/hoptell/0.1.1

## Findings with a location
- `.claude-plugin/plugin.json:18` · Credential pass-through configuration — .claude-plugin/plugin.json:18 · Credential pass-through configuration — agent relays sensitive credentials
- `server.json:20` · Credential pass-through configuration — server.json:20 · Credential pass-through configuration — agent relays sensitive credentials

## Proposed change
The attached patch removes the 2 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._