AC chain-audit-deploy
Audit and deploy blockchain smart contracts (Solidity, Sui Move, Solana). Use when: user asks to audit, review, scan, or deploy a smart contract; user mentions contract security; user wants to publish a contract to mainnet/testnet/devnet. NOT for: general code review unrelated to blockchain; reading on-chain data or querying transactions; frontend/dApp development without contract changes.
As a process C 54/100 · Has gaps — weak spots: result and completion, inputs and preconditions, consistency
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 · 8
✓ No critical or high findings
Medium and low: 8
-
medium Dangerous commands
cmd-pipe-to-shellSKILL.md:199Downloads and executes remote code from an unrecognised host (pipe to shell) (documentation of a security skill)curl -L https://foundry.paradigm.xyz | bash && foundryup
security skill -
low Risky intent
intent-offensive-securityassets/report_template.md:76Offensive-security / dual-use content (legitimate for authorised testing; review intended use)> These issues should be fixed before deployment. They may lead to loss of funds or privilege escalation.
-
low Dangerous commands
cmd-pipe-to-shellexamples/solidity/README.md:26Downloads and executes remote code from an unrecognised host (pipe to shell) (test fixture / example file; documentation of a security skill)curl -L https://foundry.paradigm.xyz | bash && foundryup
fixturesecurity skill -
low Dangerous commands
cmd-pipe-to-shellscripts/deploy_helper.py:144Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)"install_hint": "curl -L https://foundry.paradigm.xyz | bash && foundryup",
detectorcode literal -
low Risky intent
intent-offensive-securitySKILL.md:66Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Access control and privilege escalation
A further 3 matches are quotations in this security skill's documentation and are not counted as findings.
Files scanned: 23. 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 54/100
- 0Result and completion. Does not say what the result is
- 0Inputs and preconditions. Does not say what the process needs to start
- 40Consistency. Frontmatter name (chain-audit-deploy) differs from the folder (chain-audit-deploy-skill)
- 50When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (python) that frontmatter does not declare
- 70Failures and branches. 4 branches
- 100Steps. 74 steps
- 100Execution cost. Instruction body is 3477 tokens
- 100Running it twice. Mutating operations check current state
- 100Progress reporting. Reports progress
- medium Safety rules and hard prohibitions inside a skill: they belong in the system prompt, here they protect nothing
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
- +3Output format is not stated: the model decides each time
- +1No license
- +2Single-language instructions
- +4Description says when NOT to use the skill
- +3Description length 392: enough signal without eating the budget
- +4Structure: 20 headings
- +3Step-by-step instructions: 74 items
- +4Has examples (7 code blocks)
- +4Reference files are cited in the instructions (3 of 4)
- +3All 4 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 95.