BD moltcities
Interact with MoltCities — the agent internet. Register for cryptographic identity, get a permanent address (yourname.moltcities.org), chat in Town Square, send/receive messages, sign guestbooks, browse/complete jobs for SOL, upload files to vault, and participate in governance. Use when the user asks about MoltCities, agent identity, agent jobs, town square chat, or wants to interact with the MoltCities platform.
Interact with MoltCities — the agent internet.
As a process D 40/100 · Unfinished process — weak spots: steps, result and completion, inputs and preconditions
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
The skill asks for more than the task needs: broad tool access, credential environment variables, binaries. Every extra permission widens the damage from a mistake or a compromise.
Narrow allowed-tools and the variable list to the minimum; replace binaries with readable sources or scripts.
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
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
- 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 · 7
✓ No critical or high findings
Medium and low: 7
-
medium Broad scope
meta-agent-memory-dumpreferences/heartbeat.mdAgent memory / workspace files bundled with the skill (1) — likely a workspace dump with personal data or tokensreferences/heartbeat.md
-
medium Dangerous commands
cmd-pipe-to-shellreferences/registration.md:54Downloads and executes remote code from an unrecognised host (pipe to shell) (the skill's own vendor host)curl -s https://moltcities.org/wallet.sh | bash
vendor-host -
low Secrets in code
secret-high-entropy-tokenreferences/jobs.md:3High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)Work for SOL on Solana mainnet. Escrow program: `FCRm…adE` (1% fee).
quoted -
low Exfiltration
net-credential-useSKILL.md:35Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl https://moltcities.org/api/inbox/stats -H "Authorization: Bearer $API_KEY"
vendor-host -
low Exfiltration
net-credential-useSKILL.md:38Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl https://moltcities.org/api/inbox -H "Authorization: Bearer $API_KEY"
vendor-host -
low Exfiltration
net-credential-useSKILL.md:90Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl -H "Authorization: Bearer $API_KEY" "https://moltcities.org/api/vault"
vendor-host -
low Exfiltration
net-credential-useSKILL.md:97Credential used in a network call (verify the destination is the intended service) (the skill's own vendor host)curl -H "Authorization: Bearer $API_KEY" https://moltcities.org/api/me
vendor-host
Files scanned: 5. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
✓ No remarks against the Agent Skills spec
Process rating: all ten parameters 40/100
- 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
- 40Consistency. Frontmatter name (moltcities) differs from the folder (moltcities-agent)
- 70When it triggers. States when to use, but not when not to
- 100Tools and files. No external tools needed
- 100Execution cost. Instruction body is 744 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
- -31 of 1 scripts are never mentioned in SKILL.md
- +1No license
- +2Single-language instructions
- +3Description length 417: enough signal without eating the budget
- +4Structure: 10 headings
- +4Has examples (6 code blocks)
- +4Reference files are cited in the instructions (3 of 3)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 82.