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 skills add besoeasy/open-skills --skill anonymous-file-uploadgit clone --depth 1 https://github.com/besoeasy/open-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/besoeasy/open-skills/anonymous-file-upload)<a href="https://agentmods.dev/skills/besoeasy/open-skills/anonymous-file-upload"><img src="https://agentmods.dev/badge/skills/besoeasy/open-skills/anonymous-file-upload/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/besoeasy/open-skills/anonymous-file-upload"><img src="https://agentmods.dev/badge/skills/besoeasy/open-skills/anonymous-file-upload.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 7 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high Privilege Escalation · line 379 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- high Privilege Escalation · line 403 Code accesses credential files (SSH keys, AWS credentials, etc.). This could indicate credential theft attempts.Fix: Remove references to credential paths. Use environment variables or secrets managers. For docs, use placeholder paths (e.g., /path/to/config). Never load .env or token files in production code paths.
- medium MCP Rug Pull · line 29 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium MCP Rug Pull · line 478 Docker image references without a specific tag (:latest is implicit) or digest (@sha256:...) can be silently replaced by a malicious image.Fix: Pin the image: image:tag or image@sha256:abc123
- medium Data Exfiltration · line 58 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 147 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Server-Side Request Forgery · line 147 Code issues a request to a loopback, link-local, or private-range host. This can reach internal services not meant to be exposed and is a common SSRF pivot.Fix: Avoid requests to loopback/link-local/private hosts from skill code. If internal access is intended, document it and validate the target against an allowlist.
What 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 5.1 | $0.00019 | $0.04417 |
| Opus 5 | $0.00010 | $0.02209 |
| Sonnet 5 | $0.00004 | $0.00883 |
| Haiku 4.5 | $0.00002 | $0.00442 |
Grade B, and why
anonymous-file-upload scanned grade B with 2 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 11d 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.
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.
const response = await fetch('http://localhost:3232/upload', { method: 'POST', Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
Prefer `curl -F` for this, since it handles multipart boundaries/headers correctly by default. How it starts
The opening of the file, as written. The whole thing — 578 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Originless Agent Skill
Decentralized File Storage & Anonymous Content Hosting
Source: https://github.com/besoeasy/Originless
Overview
Originless is a privacy-first, decentralized file hosting backend using IPFS.
Key Principles:
- Anonymous uploads (no accounts, no tracking)
- Persistent, censorship-resistant content via IPFS
- Client-side encryption for sensitive data
- Decentralized authentication (Daku)
Endpoints:
- Self-hosted: http://localhost:3232 (Docker recommended)
- Public gateway: https://filedrop.besoeasy.com
- Blossom fallback servers:
If Docker is available, the best setup is running Originless locally:
docker run -d --restart unless-stopped --name originless \
-p 3232:3232 \
-p 4001:4001/tcp \
-p 4001:4001/udp \
-v originlessd:/data \
-e STORAGE_MAX=200GB \
ghcr.io/besoeasy/originless
That is where http://localhost:3232/upload comes from in the examples below.
Skills
upload_file_anonymously
Upload a local file to Originless/IPFS.
For .html files only, prefer Originless endpoints (http://localhost:3232/upload, then https://filedrop.besoeasy.com/upload) and do not route HTML uploads to Blossom fallback servers.
Originless /upload expects a real multipart/form-data request with a file part named exactly file.
Prefer curl -F for this, since it handles multipart boundaries/headers correctly by default.
If another client/runtime is used, it must fully replicate curl -F "file=@..." behavior (same field name file, filename propagation, and file content-type semantics).
Usage:
# HTML upload (Originless only)
curl -X POST -F "file=@/path/to/index.html" http://localhost:3232/upload || \
curl -X POST -F "file=@/path/to/index.html" https://filedrop.besoeasy.com/upload
# Self-hosted
curl -X POST -F "file=@/path/to/file.pdf" http://localhost:3232/upload
# Public gateway
curl -X POST -F "file=@/path/to/file.pdf" https://filedrop.besoeasy.com/upload
# Fallback strategy for non-HTML files (Originless first, then Blossom servers)
SERVERS=(
"http://localhost:3232/upload"
"https://filedrop.besoeasy.com/upload"
"https://blossom.primal.net/upload"
"https://24242.io/upload"
)
MAX_RETRIES=7
for ((i=0; i<MAX_RETRIES; i++)); do
idx=$((i % ${#SERVERS[@]}))
target="${SERVERS[$idx]}"
echo "Trying: $target"
if curl -fsS -X POST -F "file=@/path/to/file.pdf" "$target"; then
echo "Upload succeeded via $target"
break
fi
if [[ $i -eq $((MAX_RETRIES-1)) ]]; then
echo "All upload attempts failed after $MAX_RETRIES retries"
exit 1
fi
done
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.
- 11d ago First seen · 578 lines · 19 tokens per session scan B 6af38996e2ec
anonymous-file-upload is a skill published in the GitHub repository besoeasy/open-skills (132 stars, last pushed 6d ago), licensed MIT. It adds 19 tokens to every session and 4,417 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.
Other skills, from other repositories
Agent Wallet
Give your AI agent its own blockchain wallet without ever exposing private keys.
binance
Binance exchange integration. Trade spot, futures, and manage portfolio on the world's largest crypto exchange.
peekaboo
Capture and automate macOS UI with the Peekaboo CLI.
ax-agent-rlm
This skill helps an LLM generate correct AxAgent RLM/runtime code using @ax-llm/ax. Use when the user asks about RLM code execution, AxJSRuntime, contextFields, contextPolicy, liveRuntimeState, promptLevel, stage prompt controls, executorModelPolicy, maxRuntimeChars, agent.test(...), llmQuery(...), recursionOptions…
notifications
Send notifications through the unified notification router.
telegram-setup
Connect a Telegram bot to the Vellum Assistant gateway with automated webhook registration and credential storage.