Propose a patch

Evidence

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

diff --git a/SKILL.md b/SKILL.md
--- a/SKILL.md
+++ b/SKILL.md
@@ -32,1 +32,0 @@
-| 虾写作 | 文案/邮件/落地页/技术文章 | read / write / edit | `agents/writing-agent/MEMORY.md` | `agents/writing-agent/` | CMO调度 / 内容链路调用 |
@@ -33,1 +32,0 @@
-| 虾审核 | 内容质量审核/7维度评分/否决机制 | read / write | `agents/review-agent/MEMORY.md` | `agents/review-agent/` | 虾写作完成后触发 |
@@ -39,1 +37,0 @@
-| 虾调度 | 分发策略/渠道组合/节奏控制/内容筛选 | read / write | `agents/distribution-commander/MEMORY.md` | `agents/distribution-commander/` | CMO调度 / 内容审核通过后触发 |
@@ -40,1 +37,0 @@
-| 虾规划 | 内容策略/关键词矩阵/SEO规划 | read / write | `agents/content-strategist/MEMORY.md` | `agents/content-strategist/` | CMO调度 |
@@ -41,1 +37,0 @@
-| 虾优化 | 效果分析/四象限分类/策略反馈 | read / write | `agents/growth-analyst/MEMORY.md` | `agents/growth-analyst/` | 内容发布后数据触发 |

Zero-context hunks: apply with git apply --unidiff-zero fix.patch on the tagged source of 1.0.0. 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: agent-pool: Instructs the agent to modify its persistent memory or instruction files (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: static analysis only — behavior not yet observed.

- See the findings below.

Full trace and findings: https://killerskills.ai/skills/clawhub/agent-pool/1.0.0

## Findings with a location
- `SKILL.md:39` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:39 · Instructs the agent to modify its persistent memory or instruction files
- `SKILL.md:33` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:33 · Instructs the agent to modify its persistent memory or instruction files
- `SKILL.md:41` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:41 · Instructs the agent to modify its persistent memory or instruction files
- `SKILL.md:32` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:32 · Instructs the agent to modify its persistent memory or instruction files
- `SKILL.md:40` · Instructs the agent to modify its persistent memory or instruction files — SKILL.md:40 · Instructs the agent to modify its persistent memory or instruction files

## Proposed change
The attached patch removes the 5 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._