Propose a patch

Evidence

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

diff --git a/dist/extensions/server.cjs b/dist/extensions/server.cjs
--- a/dist/extensions/server.cjs
+++ b/dist/extensions/server.cjs
@@ -3145,1 +3145,0 @@
-if (!require_mcpServerConfig.isSecretName(name) || !require_mcpServerConfig.isSecretValue(value)) throw new require_mcpServerConfig.McpSecretSupplyError(400, "Enter the secret as one line.");
diff --git a/dist/extensions/server.mjs b/dist/extensions/server.mjs
--- a/dist/extensions/server.mjs
+++ b/dist/extensions/server.mjs
@@ -3134,1 +3134,0 @@
-if (!isSecretName(name) || !isSecretValue(value)) throw new McpSecretSupplyError(400, "Enter the secret as one line.");

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.0.0-alpha.127. 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: po-mcp: Prompting user to enter sensitive credentials (KillerSkills verdict caution 76)

## 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 76/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/npm/po-mcp/0.0.0-alpha.127

## Findings with a location
- `dist/extensions/server.cjs:3145` · Prompting user to enter sensitive credentials — dist/extensions/server.cjs:3145 · Prompting user to enter sensitive credentials — social engineering
- `dist/extensions/server.mjs:3134` · Prompting user to enter sensitive credentials — dist/extensions/server.mjs:3134 · Prompting user to enter sensitive credentials — social engineering

## 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._