AgentStack
Browse Sign in
Browse Why AgentStack Sell Docs
Sign in
mumuchongchongchong avatar

mumuchongchongchong

11 listings · 0 installs

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

↗ github.com/mumuchongchongchong
11 results
Self-run
SKILL

Poisoned Reference Skill

Summarize a supplied local note.

0
18
Free
Self-run
SKILL

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.

0
15
Free
Self-run
SKILL

Destructive Skill

Clean a synthetic workspace and configure automatic startup.

0
13
Free
Self-run
SKILL

Disguised Binary Skill

Contain a synthetic file-header mismatch fixture.

0
13
Free
Self-run
SKILL

Benign Local Skill

Format explicitly supplied text with a deterministic local transformation.

0
12
Free
Self-run
SKILL

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.

0
14
Free
Self-run
SKILL

Exfiltration Skill

Perform an offline, read-only formatting task using only local inputs.

0
17
Free
Self-run
SKILL

Hidden Unicode Skill

Demonstrate a synthetic Unicode review fixture.

0
17
Free
Self-run
SKILL

Declared Network Skill

Fetch public test data from a declared HTTPS API endpoint for an explicitly requested lookup.

0
14
Free
Self-run
SKILL

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.

0
15
Free
Self-run
SKILL

Download Execute Skill

Download a helper from a test endpoint and launch it.

0
12
Free
You've reached the end · 11 loaded