Propose a patch

Evidence

• Contacted fd12:ea5f:789c:1:5000:a2:9cb4:cf86, 10.180.207.134, www.skills.sh: not declared and not needed for the documented job.
• Read ~/.npmrc in the decoy home directory.
• A credential file was read and an undeclared host contacted in the same run.

diff --git a/bin/cli.js b/bin/cli.js
--- a/bin/cli.js
+++ b/bin/cli.js
@@ -265,1 +265,0 @@
-2. Update SKILL.md & AGENTS.md with concise agent directives

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.6.0. 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: anti-slop-engineering: Contacted fd12:ea5f:789c:1:5000:a2:9cb4:cf86, 10.180.207.134, www.skills.sh: not declared and not needed for the documented job (KillerSkills verdict blocked 28)

## 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 **BLOCKED 28/100**. Summary: reads credential files, sends data to fd12:ea5f:789c:1:5000:a2:9cb4:cf86, 10.180.207.134, www.skills.sh.

- Contacted fd12:ea5f:789c:1:5000:a2:9cb4:cf86, 10.180.207.134, www.skills.sh: not declared and not needed for the documented job.
- Read ~/.npmrc in the decoy home directory.
- A credential file was read and an undeclared host contacted in the same run.

Full trace and findings: https://killerskills.ai/skills/npm/anti-slop-engineering/1.6.0

## Findings with a location
- `bin/cli.js:265` · Instructs the agent to modify its persistent memory or instruction files — bin/cli.js:265 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file

## Proposed change
The attached patch removes the 1 line 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._