CtrlK
BlogDocsLog inGet started
Tessl Logo

security-audit

Audits Move contracts for security vulnerabilities before deployment using 7-category checklist. Triggers on: 'audit contract', 'security check', 'review security', 'check for vulnerabilities', 'security audit', 'is this secure', 'find security issues'.

82

1.41x
Quality

76%

Does it follow best practices?

Impact

95%

1.41x

Average score across 3 eval scenarios

SecuritybySnyk

Passed

No known issues

Optimize this skill with Tessl

npx tessl skill review --optimize ./.claude/skills/security-audit/SKILL.md
SKILL.md
Quality
Evals
Security

Evaluation results

100%

22%

DeFi Vault Security Review

Access control and reference safety audit

Criteria
Without context
With context

Seven categories present

0%

100%

Report header fields

100%

100%

Summary section

60%

100%

Recommendations section

100%

100%

Conclusion section

100%

100%

Finds update_fee_rate gap

100%

100%

Access control finding severity

100%

100%

Finds get_vault_mut exposure

100%

100%

Reference safety finding severity

100%

100%

Binary notation used

20%

100%

87%

42%

Staking Protocol Security Review

Input validation and arithmetic safety audit

Criteria
Without context
With context

Finds zero amount gap

100%

100%

Finds max limit gap

0%

100%

Finds stake overflow

0%

100%

Finds pool underflow

0%

100%

Finds stake underflow

70%

100%

Input validation severity

0%

20%

Arithmetic severity

30%

50%

All 7 categories reviewed

50%

100%

Names specific functions

100%

100%

Unsafe deployment conclusion

100%

100%

100%

20%

NFT Marketplace Security Audit

Object safety and generic type safety audit

Criteria
Without context
With context

Finds ConstructorRef return

100%

100%

ConstructorRef severity

100%

100%

Recommends Object<T>

100%

100%

Finds missing phantom

100%

100%

Phantom flagged as finding

100%

100%

Object Safety section addresses ConstructorRef

50%

100%

Generic Type Safety section addresses phantom

50%

100%

Testing section notes gap

80%

100%

All 7 categories present

20%

100%

Recommendations for fixes

100%

100%

Repository
aave/aptos-aave-v3
Evaluated
Agent
Claude Code
Model
Claude Sonnet 4.6

Table of Contents

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.