Propose a patch

Evidence

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

diff --git a/tests/test_harness_score.py b/tests/test_harness_score.py
--- a/tests/test_harness_score.py
+++ b/tests/test_harness_score.py
@@ -31,1 +31,0 @@
-self.write(root, "AGENTS.md", "Route to the Skill and references. Real host smoke test is separate.\n")
@@ -110,1 +109,0 @@
-self.write(root, "AGENTS.md", "已发布、来源、渠道、视觉验收、外部副作用、预检。\n")

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.1. 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: hekouwang-harness-check-skill: Instructs the agent to modify its persistent memory or instruction files (KillerSkills verdict caution 65)

## 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 65/100**. Summary: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/hekouwang-harness-check-skill/1.0.1

## Findings with a location
- `tests/test_harness_score.py:31` · Instructs the agent to modify its persistent memory or instruction files — tests/test_harness_score.py:31 · Instructs the agent to modify its persistent memory or instruction files · informational: not an instruction file
- `tests/test_harness_score.py:110` · Instructs the agent to modify its persistent memory or instruction files — tests/test_harness_score.py:110 · 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._