# mumuchongchongchong

> Open-source publisher. Listings imported from github.com/mumuchongchongchong — credited to the original author with their license.

- **Listings:** 11
- **Total installs:** 0
- **Profile:** https://agentstack.voostack.com/s/mumuchongchongchong
- **Website:** https://github.com/mumuchongchongchong

## Published listings

- [Poisoned Reference Skill](https://agentstack.voostack.com/l/skill-mumuchongchongchong-security-skills-poisoned-reference-skill) — Skill · Free · security-reviewed — `agentstack add skill-mumuchongchongchong-security-skills-poisoned-reference-skill`
  Summarize a supplied local note.
- [Audit Skill Supply Chain](https://agentstack.voostack.com/l/skill-mumuchongchongchong-security-skills-audit-skill-supply-chain) — Skill · Free · security-reviewed — `agentstack add skill-mumuchongchongchong-security-skills-audit-skill-supply-chain`
  Audit third-party Agent and Codex Skills before installation or use. Use for installation checks, Skill poisoning analysis, and supply-chain risk analysis that must inspect scripts, references, resources, trigger descriptions, and declared-versus-observed capabilities, then produce an evidence-driven installation recommendation without executing target content.
- [Inspect Encoded Artifacts](https://agentstack.voostack.com/l/skill-mumuchongchongchong-security-skills-inspect-encoded-artifacts) — Skill · Free · security-reviewed — `agentstack add skill-mumuchongchongchong-security-skills-inspect-encoded-artifacts`
  Analyze encoded security logs, HTTP parameters, JSON/JSONL fields, and suspicious text using Base64, Base64URL, URL, Hex, JWT, escape decoding, HTML entities, and bounded Gzip/Zlib decompression. Use for SOC alert triage, preliminary malicious-content analysis, and incident response when offline static inspection is required. Never execute payloads or decoded content.
- [Destructive Skill](https://agentstack.voostack.com/l/skill-mumuchongchongchong-security-skills-destructive-skill) — Skill · Free · security-reviewed — `agentstack add skill-mumuchongchongchong-security-skills-destructive-skill`
  Clean a synthetic workspace and configure automatic startup.
- [Disguised Binary Skill](https://agentstack.voostack.com/l/skill-mumuchongchongchong-security-skills-disguised-binary-skill) — Skill · Free · security-reviewed — `agentstack add skill-mumuchongchongchong-security-skills-disguised-binary-skill`
  Contain a synthetic file-header mismatch fixture.
- [Benign Local Skill](https://agentstack.voostack.com/l/skill-mumuchongchongchong-security-skills-benign-local-skill) — Skill · Free · security-reviewed — `agentstack add skill-mumuchongchongchong-security-skills-benign-local-skill`
  Format explicitly supplied text with a deterministic local transformation.
- [Exfiltration Skill](https://agentstack.voostack.com/l/skill-mumuchongchongchong-security-skills-exfiltration-skill) — Skill · Free · security-reviewed — `agentstack add skill-mumuchongchongchong-security-skills-exfiltration-skill`
  Perform an offline, read-only formatting task using only local inputs.
- [Hidden Unicode Skill](https://agentstack.voostack.com/l/skill-mumuchongchongchong-security-skills-hidden-unicode-skill) — Skill · Free · security-reviewed — `agentstack add skill-mumuchongchongchong-security-skills-hidden-unicode-skill`
  Demonstrate a synthetic Unicode review fixture.
- [Declared Network Skill](https://agentstack.voostack.com/l/skill-mumuchongchongchong-security-skills-declared-network-skill) — Skill · Free · security-reviewed — `agentstack add skill-mumuchongchongchong-security-skills-declared-network-skill`
  Fetch public test data from a declared HTTPS API endpoint for an explicitly requested lookup.
- [Audit Agent Traces](https://agentstack.voostack.com/l/skill-mumuchongchongchong-security-skills-audit-agent-traces) — Skill · Free · security-reviewed — `agentstack add skill-mumuchongchongchong-security-skills-audit-agent-traces`
  Offline reconstruction and security audit of agent execution traces from JSON, JSONL, or pasted logs. Use when Codex needs to review user input, model planning, tool calls, tool results, approvals, and final answers for prompt injection, unauthorized tools, secret exposure, missing approval, repeated-call loops, or unsupported certainty without contacting live systems.
- [Download Execute Skill](https://agentstack.voostack.com/l/skill-mumuchongchongchong-security-skills-download-execute-skill) — Skill · Free · security-reviewed — `agentstack add skill-mumuchongchongchong-security-skills-download-execute-skill`
  Download a helper from a test endpoint and launch it.

---
Seller on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Install any with `agentstack add <slug>`.