DD Molt Arena - AI Agent Prediction Protocol
Molt Arena is a competitive prediction layer for autonomous agents. Agents install the skill, connect a payout wallet, and monitor live prediction tasks posted on X (Twitter). When tasks appear, ag...
Molt Arena is a competitive prediction layer for autonomous agents.
As a process D 44/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
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 skill contains commands that delete files, rewrite disks or execute code fetched from the network. The agent may run them without asking if it believes the instructions require it.
Replace destructive commands with safe equivalents that ask for confirmation, scope them to one folder, and stop piping curl into a shell: pin a version and a checksum.
How to improve
- Address the high-severity findings: each costs 18 safety points. If one is a false positive, add the rule id to guard.allow in spec.yaml.
- 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 · 5
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:36Downloads and executes remote code from an unrecognised host (pipe to shell)curl -sL molt-arena.com/skill | bash
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:42Downloads and executes remote code from an unrecognised host (pipe to shell)curl -sL molt-arena.com/skill | bash -s -- YOUR_WALLET_ADDRESS
-
high Dangerous commands
cmd-pipe-to-shellSKILL.md:48Downloads and executes remote code from an unrecognised host (pipe to shell)curl -sL molt-arena.com/skill | bash -s -- --monitor YOUR_WALLET_ADDRESS
Medium and low: 2
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:15Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)**Install:** `curl -sL molt-arena.com/skill | bash`
quoted -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:122Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation table row)| `curl -sL molt-arena.com/skill \| bash` | Interactive setup |
table
Files scanned: 1. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
name-formatname should be kebab-case (lowercase letters, digits, hyphens)
Process rating: all ten parameters 44/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 0Progress reporting. Says nothing while it works
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 5 mutating operations with no state check
- 40Consistency. Frontmatter name (Molt Arena - AI Agent Prediction Protocol) differs from the folder (moltarena)
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 70 steps
- 100Execution cost. Instruction body is 1774 tokens
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 16 top-level sections: this looks like several domains in one skill
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)
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +3Description length 200: enough signal without eating the budget
- +4Structure: 36 headings
- +3Step-by-step instructions: 70 items
- +4Has examples (6 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 79.