Propose a patch

Evidence

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

diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -726,1 +726,0 @@
-PROSE-CLAIMS:START -- every percentage in the prose between this marker and its END must also appear inside a guarded block above, or be declared in the registr
@@ -1895,1 +1894,0 @@
-Codex MCP list showing token-optimizer installed and enabled
@@ -1901,1 +1899,0 @@
-…nd hooks The plugin supplies both automatically. For an MCP-only installation, add the guidance from [`integrations/AGENTS.md`](./integrations/AGENTS.md) to a project or global `AGENTS.md`. A ready-made standalone hook is also avail…
@@ -2002,1 +1999,0 @@
-add the recommendations from [`integrations/AGENTS.md`](./integrations/AGENTS.md)
@@ -2345,1 +2341,0 @@
-<summary>Click to expand</summary> - **optimize_text** - Compress and cache text (primary tool for token reduction) - **get_cached** - Retrieve previously cache
@@ -2373,1 +2368,0 @@
-<summary>Click to expand</summary> Optimized replacements for standard file tools with intelligent caching and diff-based updates: - **smart_read** - Read files
@@ -2402,1 +2396,0 @@
-<summary>Click to expand</summary> Intelligent caching and optimization for external data sources: - **smart_api_fetch** - HTTP requests with caching and retry 
@@ -2434,1 +2427,0 @@
-<summary>Click to expand</summary> Development workflow optimization with intelligent caching: - **smart_build** - TypeScript builds with diff-based change dete
@@ -2464,1 +2456,0 @@
-<summary>Click to expand</summary> Enterprise-grade caching strategies with 87-92% token reduction: - **smart_cache** - Multi-tier cache (L1/L2/L3) with 6 evict
@@ -2496,1 +2487,0 @@
-<summary>Click to expand</summary> Comprehensive monitoring with 88-92% token reduction through intelligent caching: - **alert_manager** - Multi-channel alertin
@@ -2525,1 +2515,0 @@
-<summary>Click to expand</summary> System-level operations with smart caching: - **smart_cron** - Scheduled task management (cron/Windows Task Scheduler) (85% r
@@ -2549,1 +2538,0 @@
-<summary>Click to expand</summary> - **intelligent-assistant** - Context-aware assistance with compact recommendations - **natural-language-query** - Natural-la
diff --git a/dist/proxy/server.js b/dist/proxy/server.js
--- a/dist/proxy/server.js
+++ b/dist/proxy/server.js
@@ -1603,1 +1603,0 @@
-throw new Error(`token-optimizer proxy: refusing to forward credentials to ${upstream} -- ` +

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 7.10.0. 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: token-optimizer-mcp: Collapsed <details> block carrying instructions (KillerSkills verdict caution 59)

## 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 59/100**. Summary: no network, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/npm/token-optimizer-mcp/7.10.0

## Findings with a location
- `README.md:2525` · Collapsed <details> block carrying instructions — README.md:2525 · Collapsed <details> block carrying instructions
- `README.md:2496` · Collapsed <details> block carrying instructions — README.md:2496 · Collapsed <details> block carrying instructions
- `README.md:2345` · Collapsed <details> block carrying instructions — README.md:2345 · Collapsed <details> block carrying instructions
- `README.md:2549` · Collapsed <details> block carrying instructions — README.md:2549 · Collapsed <details> block carrying instructions
- `README.md:2464` · Collapsed <details> block carrying instructions — README.md:2464 · Collapsed <details> block carrying instructions
- `README.md:2402` · Collapsed <details> block carrying instructions — README.md:2402 · Collapsed <details> block carrying instructions
- `README.md:2373` · Collapsed <details> block carrying instructions — README.md:2373 · Collapsed <details> block carrying instructions
- `README.md:2434` · Collapsed <details> block carrying instructions — README.md:2434 · Collapsed <details> block carrying instructions
- `dist/proxy/server.js:1603` · Credential pass-through configuration — dist/proxy/server.js:1603 · Credential pass-through configuration — agent relays sensitive credentials
- `README.md:726` · HTML comment carrying imperative instructions to the agent — README.md:726 · HTML comment carrying imperative instructions to the agent
- `README.md:1895` · Image alt text carrying instructions — README.md:1895 · Image alt text carrying instructions
- `README.md:2002` · Instructs the agent to modify its persistent memory or instruction files — README.md:2002 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## Proposed change
The attached patch removes the 13 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._