Propose a patch

Evidence

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

diff --git a/src/snipara_mcp/rlm_tools.py b/src/snipara_mcp/rlm_tools.py
--- a/src/snipara_mcp/rlm_tools.py
+++ b/src/snipara_mcp/rlm_tools.py
@@ -246,1 +246,0 @@
-raise ValueError("Snipara API key required. Set SNIPARA_API_KEY or pass api_key parameter.")
diff --git a/src/snipara_mcp/cli.py b/src/snipara_mcp/cli.py
--- a/src/snipara_mcp/cli.py
+++ b/src/snipara_mcp/cli.py
@@ -557,1 +557,0 @@
-docs_to_upload.append(("CLAUDE.md", (cwd / "CLAUDE.md").read_text()))

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 3.0.0. 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: snipara-mcp: Credential pass-through configuration (KillerSkills verdict caution 79)

## 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 79/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/snipara-mcp/3.0.0

## Findings with a location
- `src/snipara_mcp/rlm_tools.py:246` · Credential pass-through configuration — src/snipara_mcp/rlm_tools.py:246 · Credential pass-through configuration — agent relays sensitive credentials
- `src/snipara_mcp/cli.py:557` · Instructs the agent to modify its persistent memory or instruction files — src/snipara_mcp/cli.py:557 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## 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._