FF sona
Autonomous Solana wallet agent — AI reasons, Rust signs. Transfers, swaps, staking, chat, and mode switching under constitutional spend limits.
As a process F 34/100 · Will not run — weak spots: steps, result and completion, when it triggers
What is at stake
The skill contains fragments that, in the wrong hands, cost money or data. Below: what the installer risks and what the author should do.
The instructions or scripts send data out: environment variables, keys, file contents, chat history. You may never notice, because the agent performs the upload as "part of the task".
If the upload is not needed for the task, remove it: catalogs flag such skills and delist them. If it is needed, name the destination explicitly, say what leaves the machine, and give the user a switch.
How to improve
- Remove the critical guard findings (secrets, dangerous commands, hidden instructions): while they stand the skill is blocked and cannot grade above F.
- Say in the description WHEN to use the skill ("use when…", example requests): that is the agent's main cue.
- 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 · 2
-
critical Exfiltration
exfil-send-secrets-to-urlREADME.md:102Instruction to send secrets/history to an external endpoint**Security**: The plugin only connects to localhost URLs (`localhost`, `127.0.0.1`, `::1`). If `SONA_API_URL` points to a remote host, the plugin refuses to send credentials and falls back to `http://
Medium and low: 1
-
medium Exfiltration
net-redirectable-api-keyplugin.ts:30Helper sends the API key to a host configured by an environment variable — the key can be redirected to another serverAPI key + configurable base URL from environment
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
description-no-whendescription does not say WHEN to use the skill (no "use when")
Process rating: all ten parameters 34/100
- 0Steps. Prose only: no discrete steps
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Failures and branches. Linear process with no failure handling
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 40Consistency. Frontmatter name (sona) differs from the folder (sona-wallet)
- 100Tools and files. No external tools needed
- 100Execution cost. Instruction body is 882 tokens
- 100Running it twice. No mutating operations
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)
- +3No numbered steps or checklist
- +3Output format is not stated: the model decides each time
- -2localhost URLs: will not work for another user
- +2Single-language instructions
- +3Description length 143: enough signal without eating the budget
- +4Structure: 11 headings
- +4Has examples (6 code blocks)
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 68.