AD smart-contract-audit
Audit and analyze Solidity smart contracts for security vulnerabilities. Use when reviewing, auditing, or analyzing smart contracts, Solidity code, DeFi protocols, or blockchain security. Runs Slither and Aderyn static analysis, detects protocol type, spawns specialist agents for deep review, runs a triager/skeptic agent to validate findings, generates Foundry PoCs, and consolidates everything into a severity-rated report with SWC classifications and economic feasibility analysis.
Audit and analyze Solidity smart contracts for security vulnerabilities.
As a process D 42/100 · Unfinished process — weak spots: result and completion, when it triggers, inputs and preconditions
How to improve
- The SKILL.md body is over 5,000 tokens: move reference detail into references/ and load it when needed.
- 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 · 4
✓ No critical or high findings
Medium and low: 4
-
low Dangerous commands
cmd-pipe-to-shellscripts/install-tools.sh:29Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)echo "⚠️ Forge not found. Install via: curl -L https://foundry.paradigm.xyz | bash && foundryup"
detectorcode literal -
low Dangerous commands
cmd-pipe-to-shellscripts/install-tools.sh:60Downloads and executes remote code from an unrecognised host (pipe to shell) (detector / deny-list definition; string literal in code, not executed)echo " curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y"
detectorcode literal -
low Risky intent
intent-offensive-securitySKILL.md:204Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Privilege escalation paths
-
low Risky intent
intent-offensive-securitySKILL.md:208Offensive-security / dual-use content (legitimate for authorised testing; review intended use)- Check for privilege escalation chains — can a lower-privilege role gain higher privileges through a sequence of calls?
Files scanned: 15. Evidence is masked. Grey chips explain why severity was lowered.
Against the Agent Skills spec
- warning
body-longSKILL.md body ≈ 6637 tokens (recommended < 5000); move details to references/
Process rating: all ten parameters 42/100
- 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
- 20When it triggers. No condition that starts the skill
- 60Tools and files. Uses tools (bash, git) that frontmatter does not declare
- 70Execution cost. Instruction body is 6637 tokens
- 85Steps. 72 steps, 3 vague phrases
- 100Consistency. Name and required fields are in place
- 100Running it twice. Mutating operations check current state
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 485: enough signal without eating the budget
- +4Structure: 27 headings
- +3Step-by-step instructions: 72 items
- +4Has examples (12 code blocks)
- +4Reference files are cited in the instructions (9 of 11)
- +3All 3 scripts are documented
Quality base 70; lint remarks subtract, signals add up to 100. Result: 81.