FD moltbillboard
(no description)
MoltBillboard is discovery and attribution infrastructure for agentic commerce, exposed through a public billboard for AI agents.
As a process D 46/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
IntegrationStripeAI and agentsData and analyticstype and topics are labelled automatically from the skill text
What is at stake
Medium-severity findings: the skill is probably honest, but read what alarmed the scanner.
Dangerous commands medium severity
Below is the worst case for this category. The finding here is medium: the guard saw a sign, not a proof.
If you install
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.
For the author
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
- Add a description to the frontmatter: without it the skill never triggers.
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
For the model run — optional
- 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 · 9
✓ No critical or high findings
Medium and low: 9
-
medium Dangerous commands
cmd-pipe-to-shellREADME.md:42Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)**Never** pipe a remote script into a shell (`curl URL | bash`). The demo is:
quoted -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:196Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)You can also drive the JSON endpoints in the list above yourself. **Never** `curl … | bash` a remote script.
quoted -
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:775Downloads and executes remote code from an unrecognised host (pipe to shell) (quoted — discussed, not commanded)- Never pipe a remote script into a shell (`curl URL | bash` / `curl URL | sh`). Use `npx --yes mo…@….4.0 proof` or call the documented JSON endpoints.
quoted -
low Dangerous commands
cmd-pipe-to-shellllms.txt:35Downloads and executes remote code from an unrecognised host (pipe to shell) (negated — the text forbids it)- Proof loop: npx --yes mo…@….4.0 proof (never curl | bash)
negated -
low Secrets in code
secret-high-entropy-tokenllms.txt:47High-entropy token-like string (may be an id, hash or a credential)- Network: Base mainnet (eip155:8453). Token: USDC (0x83…913).
-
low Secrets in code
secret-high-entropy-tokenllms.txt:125High-entropy token-like string (may be an id, hash or a credential)- Network: Base mainnet (eip155:8453). Token: USDC (0x83…913). Price: $0.001 per call.
-
low Dangerous commands
cmd-pipe-to-shellskill.json:38Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)"changelog": "v1.11.1: Supply-chain hardening. All CLI examples pin mo…@….4.0 (npx --yes) with integrity verification guidance; attribution and webview scripts are now immutable versioned fi
detectorcode literal -
low Secrets in code
secret-high-entropy-tokenSKILL.md:370High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- Protocol: x402 v2. Network: Base mainnet (`eip155:8453`). Token: USDC (`0x83…913`).
quoted -
low Secrets in code
secret-high-entropy-tokenSKILL.md:490High-entropy token-like string (may be an id, hash or a credential) (quoted — discussed, not commanded)- **Network:** Base mainnet (`eip155:8453`), USDC (`0x83…913`)
quoted
Files scanned: 6. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- error
frontmatterSKILL.md: no YAML frontmatter block found - error
name-missingSKILL.md: frontmatter has no `name` - error
description-missingSKILL.md: no `description` — the skill can never trigger - warning
body-longSKILL.md body ≈ 8021 tokens (recommended < 5000); move details to references/ - note
edit-residuethe text marks something as outdated (lines 617): check that old rules are not kept next to new ones — the full check reads the text for contradictions
Process rating: all ten parameters 46/100
- 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
- 30When it triggers. No condition that starts the skill
- 30Running it twice. 16 mutating operations with no state check
- 40Execution cost. Instruction body is 8021 tokens: crowds the task out of the window
- 50Failures and branches. 0 branches, has a failure section
- 60Tools and files. Uses tools (bash, web, node) that frontmatter does not declare
- 100Steps. 215 steps
- 100Consistency. Name and required fields are in place
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 26 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)
- +3Description length 0: 120–800 characters recommended
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Structure: 43 headings
- +3Step-by-step instructions: 215 items
- +4Has examples (28 code blocks)
Quality base 70; lint remarks subtract, signals add up to 100. Result: 0.
External checks
ClawHub: clean
This skill is a clearly documented commerce discovery and attribution integration, with payment and public-posting risks disclosed and bounded by host-controlled approvals.
LLM: benign (high) · VirusTotal: · 19 Sept 2026