AC ssh-tunnel-swarm
Bash tool that spins up and holds open MANY concurrent SSH tunnels — both forward (-L) and reverse (-R) — driven by a plain-text rules file. One connection block per host: a header line `user@host:port=/path/to/private/key` followed by one or more tunnel lines `forward|reverse local-iface:local-port:remote-iface:remote-port`, blocks separated by blank lines. Each host connection runs in its own background loop (`ssh -N -i <key> -o ExitOnForwardFailure=yes -o ServerAliveInterval=30 -o ServerAliveCountMax=3 -o StrictHostKeyChecking=yes`) and auto-reconnects with a 5s backoff on drop; SIGINT/SIGTERM tears every tunnel down cleanly. Configured entirely via env vars (RULES_FILE, LOG_ENABLED, LOG_FILE, LOG_LEVEL) — no CLI flags. No password auth, key-based only. Use when the user wants to set up/manage multiple SSH forward or reverse tunnels from a single rules file across one or many hosts.
Bash tool that spins up and holds open MANY concurrent SSH tunnels — both forward (-L) and reverse (-R) — driven by a plain-text rules file.
As a process C 59/100 · Has gaps — weak spots: result and completion, inputs and preconditions
How to improve
- Your own cases (evals/evals.json, 4–6 real requests with expected answers): the full check would then run those instead of a model-drafted suite.
- A spec.yaml with trigger phrases and assertions — a behaviour contract for CI; `skilltest init` writes a template.
Guard findings · 3
✓ No critical or high findings
Medium and low: 3
-
low Dangerous commands
cmd-pipe-to-shell-known-hostreferences/setup.md:20Pipe-to-shell installer from a well-known host (still executes remote code) (documentation of a security skill)wget -qO- https://raw.githubusercontent.com/psyb0t/ssh-tunnel-swarm/master/tools/downloader.sh | bash
security skill -
low Dangerous commands
cmd-privilegereferences/setup.md:32Privilege escalation / world-writable permissions (documentation of a security skill)sudo mv ssh-tunnel-swarm /usr/local/bin/
security skill -
low Dangerous commands
cmd-shell-rcreferences/setup.md:44Writes to a shell startup file (documentation of a security skill)echo 'export PATH="$HOME/bin:$PATH"' >> ~/.bashrc # or ~/.zshrc for zsh
security skill
Files scanned: 3. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- note
frontmatter-keyunknown frontmatter key "homepage" - note
frontmatter-keyunknown frontmatter key "permissions"
Process rating: all ten parameters 59/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 70When it triggers. States when to use, but not when not to
- 100Steps. 24 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 1282 tokens
- 100Running it twice. No mutating operations
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
Everything here is measured from the skill text rather than judged by a model, so the numbers are checkable. A parameter weighs more when it is a more common reason for the process to stall.
Quality signals
- +5Description has no quoted example phrases that should trigger the skill
- +4Description does not say when NOT to use the skill (false activations)
- +3Description length 898: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +1No license
- +2Single-language instructions
- +4Structure: 7 headings
- +3Step-by-step instructions: 24 items
- +4Has examples (3 code blocks)
- +4Reference files are cited in the instructions (1 of 1)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.