← auto-research-claw@1.0.0
Propose a patch
A fix the maintainer can act on, with the evidence attached. It opens under your GitHub account in your browser; KillerSkills holds no token and never modifies the package. The fix is verified the only way we verify anything: the next crawl re-runs the new version in the honeypot. 39 · Blocked
Evidence
The sandbox observed nothing beyond the static findings; the proposal cites those.
Diff · removes 15 caught lines
Download .patchdiff --git a/config.researchclaw.example.yaml b/config.researchclaw.example.yaml --- a/config.researchclaw.example.yaml +++ b/config.researchclaw.example.yaml @@ -90,1 +90,0 @@ -key_path: "" # Path to private key (default: ~/.ssh/id_rsa) @@ -122,1 +121,0 @@ -# key_path: "~/.ssh/id_rsa" @@ -132,1 +130,0 @@ -# key_path: "~/.ssh/id_rsa" diff --git a/docs/README_DE.md b/docs/README_DE.md --- a/docs/README_DE.md +++ b/docs/README_DE.md @@ -191,1 +191,0 @@ -<summary>💡 Was unter der Haube passiert</summary> 1. OpenClaw liest `RESEARCHCLAW_AGENTS.md` → lernt die Forschungs-Orchestrator-Rolle 2. OpenClaw liest `READM diff --git a/docs/README_JA.md b/docs/README_JA.md --- a/docs/README_JA.md +++ b/docs/README_JA.md @@ -191,1 +191,0 @@ -<summary>💡 内部で何が起きているか</summary> 1. OpenClawが`RESEARCHCLAW_AGENTS.md`を読み取り → 研究オーケストレーターの役割を学習 2. OpenClawが`README.md`を読み取り → インストールとパイプライン構造を理解 3. OpenClawが`c diff --git a/docs/README_AR.md b/docs/README_AR.md --- a/docs/README_AR.md +++ b/docs/README_AR.md @@ -191,1 +191,0 @@ -<summary>💡 ماذا يحدث خلف الكواليس</summary> 1. يقرأ OpenClaw ملف `RESEARCHCLAW_AGENTS.md` → يتعلم دور منسّق البحث 2. يقرأ OpenClaw ملف `README.md` → يفهم التثب diff --git a/docs/README_KO.md b/docs/README_KO.md --- a/docs/README_KO.md +++ b/docs/README_KO.md @@ -191,1 +191,0 @@ -<summary>💡 내부 동작 과정</summary> 1. OpenClaw이 `RESEARCHCLAW_AGENTS.md`를 읽고 → 연구 오케스트레이터 역할을 학습 2. OpenClaw이 `README.md`를 읽고 → 설치 및 파이프라인 구조를 이해 3. OpenClaw이 `conf diff --git a/researchclaw/experiment/ssh_sandbox.py b/researchclaw/experiment/ssh_sandbox.py --- a/researchclaw/experiment/ssh_sandbox.py +++ b/researchclaw/experiment/ssh_sandbox.py @@ -258,1 +258,0 @@ -# 1. HOME override — prevents reading ~/.ssh, ~/.bashrc, etc. diff --git a/docs/README_CN.md b/docs/README_CN.md --- a/docs/README_CN.md +++ b/docs/README_CN.md @@ -191,1 +191,0 @@ -<summary>💡 底层发生了什么</summary> 1. OpenClaw 读取 `RESEARCHCLAW_AGENTS.md` → 学习研究编排器角色 2. OpenClaw 读取 `README.md` → 理解安装方式和流水线结构 3. OpenClaw 复制 `config.researchclaw. diff --git a/README.md b/README.md --- a/README.md +++ b/README.md @@ -190,1 +190,0 @@ -<summary>💡 What happens under the hood</summary> 1. OpenClaw reads `RESEARCHCLAW_AGENTS.md` → learns the research orchestrator role 2. OpenClaw reads `README.m diff --git a/docs/README_FR.md b/docs/README_FR.md --- a/docs/README_FR.md +++ b/docs/README_FR.md @@ -191,1 +191,0 @@ -<summary>💡 Ce qui se passe en coulisses</summary> 1. OpenClaw lit `RESEARCHCLAW_AGENTS.md` → apprend le role d'orchestrateur de recherche 2. OpenClaw lit `READ diff --git a/docs/README_ES.md b/docs/README_ES.md --- a/docs/README_ES.md +++ b/docs/README_ES.md @@ -191,1 +191,0 @@ -<summary>💡 Que sucede internamente</summary> 1. OpenClaw lee `RESEARCHCLAW_AGENTS.md` → aprende el rol de orquestador de investigacion 2. OpenClaw lee `README. diff --git a/docs/README_PT.md b/docs/README_PT.md --- a/docs/README_PT.md +++ b/docs/README_PT.md @@ -191,1 +191,0 @@ -<summary>💡 O que acontece por baixo dos panos</summary> 1. O OpenClaw lê `RESEARCHCLAW_AGENTS.md` → aprende o papel de orquestrador de pesquisa 2. O OpenClaw l diff --git a/docs/README_RU.md b/docs/README_RU.md --- a/docs/README_RU.md +++ b/docs/README_RU.md @@ -185,1 +185,0 @@ -<summary>💡 Что происходит под капотом</summary> 1. OpenClaw читает `RESEARCHCLAW_AGENTS.md` → принимает на себя роль исследовательского оркестратора 2. OpenCla diff --git a/docs/showcase/SHOWCASE.md b/docs/showcase/SHOWCASE.md --- a/docs/showcase/SHOWCASE.md +++ b/docs/showcase/SHOWCASE.md @@ -413,1 +413,0 @@ -<summary>🖼️ <b>Auto-Generated Framework Diagram</b> — FAME Architecture</summary> <br> <p align="center"> <img src="thumbnails/framework_VII_fame_token_merging
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: auto-research-claw: References a credential file in the home directory (KillerSkills verdict blocked 39)
## 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 39/100**. Summary: static analysis only — behavior not yet observed. - See the findings below. Full trace and findings: https://killerskills.ai/skills/clawhub/auto-research-claw/1.0.0 ## Findings with a location - `config.researchclaw.example.yaml:122` · References a credential file in the home directory — config.researchclaw.example.yaml:122 · References a credential file in the home directory - `docs/README_DE.md:191` · Collapsed <details> block carrying instructions — docs/README_DE.md:191 · Collapsed <details> block carrying instructions - `docs/README_JA.md:191` · Collapsed <details> block carrying instructions — docs/README_JA.md:191 · Collapsed <details> block carrying instructions - `docs/README_AR.md:191` · Collapsed <details> block carrying instructions — docs/README_AR.md:191 · Collapsed <details> block carrying instructions - `docs/README_KO.md:191` · Collapsed <details> block carrying instructions — docs/README_KO.md:191 · Collapsed <details> block carrying instructions - `researchclaw/experiment/ssh_sandbox.py:258` · Reads credential paths from the home directory — researchclaw/experiment/ssh_sandbox.py:258 · Reads credential paths from the home directory - `docs/README_CN.md:191` · Collapsed <details> block carrying instructions — docs/README_CN.md:191 · Collapsed <details> block carrying instructions - `README.md:190` · Collapsed <details> block carrying instructions — README.md:190 · Collapsed <details> block carrying instructions - `docs/README_FR.md:191` · Collapsed <details> block carrying instructions — docs/README_FR.md:191 · Collapsed <details> block carrying instructions - `docs/README_ES.md:191` · Collapsed <details> block carrying instructions — docs/README_ES.md:191 · Collapsed <details> block carrying instructions - `docs/README_PT.md:191` · Collapsed <details> block carrying instructions — docs/README_PT.md:191 · Collapsed <details> block carrying instructions - `config.researchclaw.example.yaml:132` · References a credential file in the home directory — config.researchclaw.example.yaml:132 · References a credential file in the home directory ## Proposed change The attached patch removes the 15 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._
# or from a terminal, under your own account: gh repo fork aiming-lab/AutoResearchClaw --clone && cd AutoResearchClaw curl -s https://killerskills.ai/skills/clawhub/auto-research-claw/1.0.0/patch.diff | git apply --unidiff-zero git checkout -b killerskills/1.0.0 && git commit -am "auto-research-claw: References a credential file in the home directory" gh pr create --fill --body-file <(curl -s https://killerskills.ai/skills/clawhub/auto-research-claw/1.0.0/patch.md)
We count proposals opened, not merged: a merge shows up as a new version that the crawl re-runs. Disputes: the maintainer can contest the verdict from its page; a person reviews it and the outcome is published.