Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add skills/curiouslearnerdev/online_tools-ai/ctf-miscnpx skills add CuriousLearnerDev/Online_Tools-AI --skill ctf-miscgit clone --depth 1 https://github.com/CuriousLearnerDev/Online_Tools-AIWhat it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00122 | $0.07196 |
| Opus 5 | $0.00061 | $0.03598 |
| Sonnet 5 | $0.00024 | $0.01439 |
| Haiku 4.5 | $0.00012 | $0.00720 |
Grade F, and why
ctf-misc scanned grade F with 6 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 3d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Asks the agent to reveal its instructionsmediumSystem prompt leakage
Directions to print, repeat or translate the system prompt extract configuration the operator did not intend to expose.
- **Emulator ROM-switching:** `/load` replaces ROM but preserves CPU state (registers, RAM, PC). Switch ROMs at specific PCs to combine INIT from one ROM with display instructions from another → read protected memory. Se Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
curl -s -X POST -H "Authorization: Token $CTF_TOKEN" -H "Content-Type: application/json" "$CTF_URL/api/v1/challenges/attempt" -d "{\"challenge_id\": $CID, \"submission\": \"flag{...}\"}" Harvests environment variableshighData exfiltration
Enumerating or grepping the environment for keys collects credentials unrelated to what the mod says it does.
`COPY (SELECT '') TO PROGRAM 'cmd'` executes OS commands as postgres. `pg_read_file('/path')` reads files. Extract credentials from `pg_basebackup` archives (`global/1260` = `pg_authid`). SSH tunnel to Unix sockets: `ssh Encoded or obfuscated payloadhighSupply chain
base64 or hex that is decoded and executed hides what actually runs from anyone reading the file.
python3 -c "__import__('os').system('id')" Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Detect CTFd (`curl -s "$CTF_URL/api/v1/" | head -5`) and interact via API. **Ask the user for their API token** (CTFd Settings > Access Tokens) — it is not provided by default. Then use `Authorization: Token $CTF_TOKEN` Runs shell commandslowCapability
Expected in a hook, worth knowing in a rule or an instructions file.
`rvim` blocks `:!` but `:python3 import os; os.system("cmd")` executes arbitrary commands. Check `:version` for `+python3`/`+lua`/`+ruby`. See [games-and-vms-3.md](games-and-vms-3.md#rvim-jail-escape-via-custom-vimrc-wit The source is not reproduced here
No licence file
A repository with no LICENSE is all rights reserved by default, so the body is not copied here. The metadata, the measurements and the link are.
What ships with it
12 files beside SKILL.md in the same directory: the scripts, references and assets a skill reads on demand. Not counted in the per-session cost; read them before you install if any of them is executable.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 3d ago First seen · 497 lines · 122 tokens per session scan F 7c93032c00d9
ctf-misc is a skill published in the GitHub repository CuriousLearnerDev/Online_Tools-AI (52 stars, last pushed 1mo ago), with no licence file. It adds 122 tokens to every session and 7,196 once invoked, about $0.0006 per session on Opus 5. A static security scan graded it F with 6 findings (asks the agent to reveal its instructions, sends data to an external url, harvests environment variables). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
brainstorming
You MUST use this before any creative work - creating features, building components, adding functionality, or modifying behavior. Explores user intent, requirements and design before implementation.
auto-perf-optimize
Run agent-driven VS Code performance or memory investigations. Use when asked to launch Code OSS, automate a VS Code scenario, run the Chat memory smoke runner, capture renderer heap snapshots, take workflow screenshots, compare run summaries, or drive a repeatable scenario before heap-snapshot analysis.
chat-perf
Run chat perf benchmarks and memory leak checks against the local dev build or any published VS Code version. Use when investigating chat rendering regressions, validating perf-sensitive changes to chat UI, or checking for memory leaks in the chat response pipeline.
chat-pet-sprite-creation
Use when creating or changing VS Code chat pet sprite art, sprite sheets, state animations, eye treatments, Stable/Insiders variants, or pet transitions under src/vs/workbench/contrib/chat/browser/widget/media/chatPet.
cpu-profile-analysis
Analyze V8/Chrome CPU profiles (.cpuprofile) and DevTools trace files (Trace-.json). Use when: profiling performance, investigating slow functions, comparing code paths, finding bottlenecks, analyzing timeToRequest, understanding call trees from sampling profiler data, analyzing layout/paint/rendering, investigating…