Propose a patch

Evidence

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

diff --git a/src/platform/win32/secrets.mjs b/src/platform/win32/secrets.mjs
--- a/src/platform/win32/secrets.mjs
+++ b/src/platform/win32/secrets.mjs
@@ -23,1 +23,0 @@
-public static class ThriftyRelayCredentialNative {
@@ -59,1 +58,0 @@
-$credential = [Activator]::CreateInstance([type][ThriftyRelayCredentialNative+Credential])
@@ -66,1 +64,0 @@
-if (-not [ThriftyRelayCredentialNative]::CredWrite([ref]$credential, 0)) { throw 'write failed' }
@@ -69,1 +66,0 @@
-if ([ThriftyRelayCredentialNative]::CredDelete([string]$payload.target, 1, 0)) {
@@ -75,1 +71,0 @@
-if ([ThriftyRelayCredentialNative]::CredRead([string]$payload.target, 1, 0, [ref]$credentialPointer)) {

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.4.1. 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: thriftyrelay: Credential pass-through configuration (KillerSkills verdict caution 74)

## 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 74/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/glama/thriftyrelay/0.4.1

## Findings with a location
- `src/platform/win32/secrets.mjs:59` · Credential pass-through configuration — src/platform/win32/secrets.mjs:59 · Credential pass-through configuration — agent relays sensitive credentials
- `src/platform/win32/secrets.mjs:23` · Credential pass-through configuration — src/platform/win32/secrets.mjs:23 · Credential pass-through configuration — agent relays sensitive credentials
- `src/platform/win32/secrets.mjs:66` · Credential pass-through configuration — src/platform/win32/secrets.mjs:66 · Credential pass-through configuration — agent relays sensitive credentials
- `src/platform/win32/secrets.mjs:75` · Credential pass-through configuration — src/platform/win32/secrets.mjs:75 · Credential pass-through configuration — agent relays sensitive credentials
- `src/platform/win32/secrets.mjs:69` · Credential pass-through configuration — src/platform/win32/secrets.mjs:69 · Credential pass-through configuration — agent relays sensitive credentials

## Proposed change
The attached patch removes the 5 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._