BC safelink
Secure agent-to-agent hiring and execution skill for OpenClaw MCP with escrowed settlement, x402 facilitator payments, ERC-8004 identity/reputation checks, strict replay protection, DNS-safe endpoint validation, and MPC wallet signing. Use when building or operating production A2A workflows that require proof-before-settlement, policy gating, risk-scored transactions, and beginner-friendly wallet setup.
As a process C 51/100 · Has gaps — weak spots: result and completion, when it triggers, 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 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 · 5
✓ No critical or high findings
Medium and low: 5
-
medium Dangerous commands
cmd-pipe-to-shellscripts/deploy-contracts.ts:6Downloads and executes remote code from an unrecognised host (pipe to shell) (code comment)* 1. Install Foundry: curl -L https://foundry.paradigm.xyz | bash && foundryup
comment -
medium Dangerous commands
cmd-pipe-to-shellscripts/deploy-contracts.ts:48Downloads and executes remote code from an unrecognised host (pipe to shell) (string literal in code, not executed)" Install: curl -L https://foundry.paradigm.xyz | bash && foundryup"
code literal -
low Instruction override
en-ignore-previous_meta.json:86Instruction-override phrase ("ignore previous instructions") (detector / deny-list definition; security demo / example)"securityNotes": "Test files under tests/stress/ contain literal prompt-injection strings (e.g. 'Ignore all previous instructions') as adversarial test fixtures that verify the input-gate blocks them.
detectordemo
A further 2 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 16. 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 51/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 20When it triggers. No condition that starts the skill
- 30Running it twice. 15 mutating operations with no state check
- 55Failures and branches. 1 branches
- 60Tools and files. Uses tools (bash, web) that frontmatter does not declare
- 100Steps. 135 steps
- 100Consistency. Name and required fields are in place
- 100Execution cost. Instruction body is 3414 tokens
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
- low 14 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
- -2localhost URLs: will not work for another user
- +2Single-language instructions
- +3Description length 406: enough signal without eating the budget
- +4Structure: 25 headings
- +3Step-by-step instructions: 135 items
- +4Has examples (17 code blocks)
- +3All 2 scripts are documented
- +1License stated
Quality base 70; lint remarks subtract, signals add up to 100. Result: 86.