clawdbot-knowledge@1.0.0
CAUTION· install onlyPublisher claims: "MCP Server Orchestral Integration - Integriert den fortgeschrittenen MCP Server mit 27-28 Super-Agenten in das Super-Skill-Ökosystem. Ermöglicht DeepMaster-A..." Observed in sandbox: no network, touches nothing outside the project, writes no memory.
Coverage
Bundled scripts ran with no arguments; no agent task scenario for this bundle.- Tested
- 8 of 36 bundled scripts run with no arguments (the rest were not run: per-bundle cap), with decoy credentials in the environment · every file read, file written and host contacted by what ran
- Not tested
- use of the skill by an agent
Is [email protected] safe to install?
KillerSkills ran it in the KillerSkills honeypot sandbox (2 scenarios; bundled scripts ran with no arguments; no agent task scenario for this bundle) on 2026-11-18 and scored it 78/100 (Caution). It is not known to be malicious, but it has behaviour or code a security policy should decide on before install. Notable findings: Access to sensitive file paths; Access to sensitive file paths; Destructive file system command detected. Summary: no network, touches nothing outside the project, writes no memory.
Behavior trace
Honeypot run · 1 s · 2 scenarios · 0 deviationsStatic findings
system:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Instructions:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.5. **Secrets**: Niemals committen; `.env` + `.gitignore`; Logs redactedFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.load_dotenv('.env.real')Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.rm -f /tmp/revolutionary_system_pids.txtFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# Lade echte Umgebungsvariablen aus .env.realFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.load_dotenv('.env.real')Fix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.kill $DASHBOARD_PIDFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- When you learn a lesson → update AGENTS.md, TOOLS.md, or the relevant skillFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.2. **Review Regularly**: Update MEMORY.md from daily filesFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- **Review and update MEMORY.md** (see below)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.kill $API_PIDFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.kill $INTEGRATOR_PIDFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.self.logger.info("✅ MCP-Server erfolgreich abgeschlossen!")Fix: Namespace tool names and keep tool descriptions literal; no instructions to the agent inside them.- Over time, review your daily files and update MEMORY.md with what's worth keepingFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.3. Update `MEMORY.md` with distilled learningsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.-----END RSA PRIVATE KEY-----"Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- ✅ MEMORY.md - Complete update with all systems (this file)Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.kill $STREAMLIT_PIDFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.- You can **read, edit, and update** MEMORY.md freely in main sessionsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.kill $pidFix: Build commands from fixed arguments; do not interpolate untrusted strings into a shell.# Lade echte Umgebungsvariablen aus .env.realFix: Stop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.3. **Update MEMORY.md**: Update `MEMORY.md` with distilled learningsFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- **Lesson Learning**: When you learn a lesson → update AGENTS.md, TOOLS.md, or skillFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.- Review and update MEMORY.mdFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.git add AGENTS.md SOUL.md TOOLS.md IDENTITY.md USER.md HEARTBEAT.md memory/Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.System:Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.Cost to the agent
Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.
Known vulnerabilities
Vulnerability advisories (OSV) cover npm and PyPI packages; this registry has no advisory database.
What would make this Verified
2 points to 80 · weights: behavior 45%, static 25%, prompt 15%, publisher 15%- Unclaimed publisher≈ +8 on the totalClaim f4t1i: a verified publisher gets +50 on publisher trust. It is free and usually instant with GitHub sign-in.
- Access to sensitive file paths≈ +4 on the totalStop enumerating or reading credential locations; take secrets from a declared environment variable the user sets on purpose.
- Destructive file system command detected≈ +4 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- Process kill command≈ +2 on the totalBuild commands from fixed arguments; do not interpolate untrusted strings into a shell.
- MCP server using network transport (SSE/HTTP)≈ +2 on the totalNamespace tool names and keep tool descriptions literal; no instructions to the agent inside them.