Create free SSH tunnels to expose local ports to the internet using tinyfi.sh. Use when you need to share a locally running app, test webhooks, demo a prototype, or get a public HTTPS URL for any local service — no signup or authentication required.
Security Analysis
medium confidenceThe instructions match the stated purpose (creating SSH tunnels) but there are provenance and safety gaps — the skill omits that it requires ssh, auto-accepts host keys, and points users to an unverified remote service (tinyfi.sh) that will see your traffic.
The SKILL.md explicitly requires SSH to create remote port forwards (ssh -R ... tinyfi.sh), but the skill metadata declares no required binaries. That mismatch is incoherent: the skill needs ssh to work but doesn't declare it. Additionally the skill points traffic to tinyfi.sh (no homepage or source listed), so the external dependency is not documented or vetted in the metadata.
Runtime instructions tell the agent to run ssh -R and to use -o StrictHostKeyChecking=accept-new (auto-accept new host keys) and to run the SSH command in the background. Auto-accepting host keys increases risk of connecting to an impostor server; running the tunnel exposes arbitrary local services to the remote operator, including any sensitive endpoints or credentials sent over those connections. The instructions do not require verifying server fingerprints or limiting what is exposed.
This is an instruction-only skill with no install steps or code to write to disk, which is lower risk. There is no download or install mechanism to review.
The skill declares no environment variables or credentials and the instructions do not request any secrets. That is proportionate. However, creating a tunnel inherently exposes local network services and any data those services accept to the remote server (tinyfi.sh), which is a privacy/security consideration not reflected in metadata.
The skill is not always-enabled and does not request elevated platform privileges. It does instruct the agent to run background SSH processes (which is normal for a tunneling tool), but autonomous execution would let the agent open network tunnels — a capability worth restricting to trusted skills or explicit user approval.
Guidance
Before installing or letting an agent run this skill, consider: (1) The metadata fails to list 'ssh' as a required binary even though the instructions rely on it — ask the publisher to correct that. (2) tinyfi.sh has no listed homepage or source in the skill; verify who operates tinyfi.sh and whether you trust that operator, because all tunneled traffic (and URLs) will pass through their servers. (3) The recommended ssh option StrictHostKeyChecking=accept-new auto-accepts host keys — this can allow man-in-the-middle connections; prefer verifying the server fingerprint manually. (4) Never expose services that handle secrets, authentication tokens, private keys, or production databases via an untrusted tunnel. If you must test webhooks/demos, run on ephemeral test data behind authentication. (5) If you don't fully trust tinyfi.sh or autonomous agent execution, run the ssh command yourself manually and inspect the connection, or use a well-known tunneling provider (or your own SSH server) with documented security practices. (6) Consider limiting the agent's ability to execute background network processes unless you explicitly trust the skill and its operator.
Latest Release
v1.0.0
- Initial release of the tunneling skill. - Easily expose any local port to the public internet via the TinyFish (tinyfi.sh) SSH tunnel service. - No signup or authentication required; just use SSH. - Supports choosing random or custom subdomains for your public URL. - Includes keep-alive instructions for stable long-running tunnels. - Documents usage guidelines, common ports, and service rate limits.
Popular Skills
Published by @simantak-dabhade on ClawHub
