Propose a patch

Evidence

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

diff --git a/docs/INTEGRATION_GUIDE.md b/docs/INTEGRATION_GUIDE.md
--- a/docs/INTEGRATION_GUIDE.md
+++ b/docs/INTEGRATION_GUIDE.md
@@ -52,1 +52,0 @@
-✅ **Auto-Update CLAUDE.md**: Config files updated intelligently
@@ -122,1 +121,0 @@
-4. **Auto-update triggered**: `./CLAUDE.md` updated automatically
@@ -549,1 +547,0 @@
-**Before**: Manually edit CLAUDE.md after corrections
diff --git a/src/mcp_standards/server.py b/src/mcp_standards/server.py
--- a/src/mcp_standards/server.py
+++ b/src/mcp_standards/server.py
@@ -228,1 +228,0 @@
-description="Update CLAUDE.md file with learned preferences (creates backup first)",
@@ -594,1 +593,0 @@
-"message": f"Found {len(suggestions)} suggestion(s) for CLAUDE.md update"
@@ -602,1 +600,0 @@
-"""Update CLAUDE.md file with learned preferences"""
diff --git a/README.md b/README.md
--- a/README.md
+++ b/README.md
@@ -328,1 +328,0 @@
-6. Run `suggest_claudemd_update()` → Get suggestion to add to CLAUDE.md
@@ -340,1 +339,0 @@
-4. **Update CLAUDE.md** when confidence scores are high (0.7+)
@@ -358,1 +356,0 @@
-User Correction → Pattern Extraction → Frequency Tracking → Confidence Scoring → Preference Promotion → CLAUDE.md Update
diff --git a/PKG-INFO b/PKG-INFO
--- a/PKG-INFO
+++ b/PKG-INFO
@@ -352,1 +352,0 @@
-6. Run `suggest_claudemd_update()` → Get suggestion to add to CLAUDE.md
@@ -364,1 +363,0 @@
-4. **Update CLAUDE.md** when confidence scores are high (0.7+)
@@ -382,1 +380,0 @@
-User Correction → Pattern Extraction → Frequency Tracking → Confidence Scoring → Preference Promotion → CLAUDE.md Update
diff --git a/docs/guides/QUICKSTART.md b/docs/guides/QUICKSTART.md
--- a/docs/guides/QUICKSTART.md
+++ b/docs/guides/QUICKSTART.md
@@ -57,1 +57,0 @@
-// → CLAUDE.md will update
diff --git a/src/mcp_standards/intelligence/claudemd_manager.py b/src/mcp_standards/intelligence/claudemd_manager.py
--- a/src/mcp_standards/intelligence/claudemd_manager.py
+++ b/src/mcp_standards/intelligence/claudemd_manager.py
@@ -238,1 +238,0 @@
-Update CLAUDE.md file with learned preferences
diff --git a/docs/SELF-LEARNING-PRD.md b/docs/SELF-LEARNING-PRD.md
--- a/docs/SELF-LEARNING-PRD.md
+++ b/docs/SELF-LEARNING-PRD.md
@@ -256,1 +256,0 @@
-If pattern repeats 3+: Update CLAUDE.md
@@ -270,1 +269,0 @@
-├─ Update CLAUDE.md
diff --git a/src/mcp_standards/hooks/capture_hook.py b/src/mcp_standards/hooks/capture_hook.py
--- a/src/mcp_standards/hooks/capture_hook.py
+++ b/src/mcp_standards/hooks/capture_hook.py
@@ -8,1 +8,0 @@
-3. Update CLAUDE.md files
diff --git a/docs/CONFIG_STANDARDS.md b/docs/CONFIG_STANDARDS.md
--- a/docs/CONFIG_STANDARDS.md
+++ b/docs/CONFIG_STANDARDS.md
@@ -372,1 +372,0 @@
-- Primary updates: Always update CLAUDE.md

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.0a2. 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: mcp-standards: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 53)

## 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 53/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/mcp-standards/0.1.0a2

## Findings with a location
- `docs/INTEGRATION_GUIDE.md:122` · Instructs the agent to modify its persistent memory or instruction files — docs/INTEGRATION_GUIDE.md:122 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `src/mcp_standards/server.py:228` · Instructs the agent to modify its persistent memory or instruction files — src/mcp_standards/server.py:228 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `docs/INTEGRATION_GUIDE.md:52` · Instructs the agent to modify its persistent memory or instruction files — docs/INTEGRATION_GUIDE.md:52 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `README.md:340` · Instructs the agent to modify its persistent memory or instruction files — README.md:340 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `PKG-INFO:364` · Instructs the agent to modify its persistent memory or instruction files — PKG-INFO:364 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `docs/guides/QUICKSTART.md:57` · Instructs the agent to modify its persistent memory or instruction files — docs/guides/QUICKSTART.md:57 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `PKG-INFO:382` · Instructs the agent to modify its persistent memory or instruction files — PKG-INFO:382 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `README.md:328` · Instructs the agent to modify its persistent memory or instruction files — README.md:328 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `src/mcp_standards/intelligence/claudemd_manager.py:238` · Instructs the agent to modify its persistent memory or instruction files — src/mcp_standards/intelligence/claudemd_manager.py:238 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `docs/SELF-LEARNING-PRD.md:270` · Instructs the agent to modify its persistent memory or instruction files — docs/SELF-LEARNING-PRD.md:270 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `src/mcp_standards/server.py:602` · Instructs the agent to modify its persistent memory or instruction files — src/mcp_standards/server.py:602 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `PKG-INFO:352` · Instructs the agent to modify its persistent memory or instruction files — PKG-INFO:352 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## Proposed change
The attached patch removes the 18 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._