Propose a patch

Evidence

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

diff --git a/.coderabbit.yaml b/.coderabbit.yaml
--- a/.coderabbit.yaml
+++ b/.coderabbit.yaml
@@ -34,1 +34,0 @@
-- label: "👨‍🚀 crew-backend"
diff --git a/docs/ai-docs/cc_slash_commands.md b/docs/ai-docs/cc_slash_commands.md
--- a/docs/ai-docs/cc_slash_commands.md
+++ b/docs/ai-docs/cc_slash_commands.md
@@ -21,1 +21,0 @@
-| `/memory`                 | Edit CLAUDE.md memory files                                                    |
diff --git a/docs/ai-docs/cc_common_workflows.md b/docs/ai-docs/cc_common_workflows.md
--- a/docs/ai-docs/cc_common_workflows.md
+++ b/docs/ai-docs/cc_common_workflows.md
@@ -373,1 +373,0 @@
-* @ file references add CLAUDE.md in the file's directory and parent directories to context
diff --git a/.github/copilot-instructions.md b/.github/copilot-instructions.md
--- a/.github/copilot-instructions.md
+++ b/.github/copilot-instructions.md
@@ -64,1 +64,0 @@
-1. Update CLAUDE.md for AI-specific guidance

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 0.1.6. 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: mseep-mcp-zammad: Hidden zero-width characters detected (KillerSkills verdict caution 70)

## 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 70/100**. Summary: calls astral.sh only, touches nothing outside the project, writes no memory.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/pypi/mseep-mcp-zammad/0.1.6

## Findings with a location
- `.coderabbit.yaml:34` · Hidden zero-width characters detected — .coderabbit.yaml:34 · Hidden zero-width characters detected — may conceal content
- `docs/ai-docs/cc_slash_commands.md:21` · Instructs the agent to modify its persistent memory or instruction files — docs/ai-docs/cc_slash_commands.md:21 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `docs/ai-docs/cc_common_workflows.md:373` · Instructs the agent to modify its persistent memory or instruction files — docs/ai-docs/cc_common_workflows.md:373 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `.github/copilot-instructions.md:64` · Instructs the agent to modify its persistent memory or instruction files — .github/copilot-instructions.md:64 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## Proposed change
The attached patch removes the 4 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._