AgentSec

[AgentSec @agentsec_sh]

Audit your own skill in 5 seconds:

npx agentsec

Full per-rule matrix, JSON + HTML + SARIF outputs, OWASP-aligned scoring.

https://t.co/6OkYWnXbge

Building an agent skill or auditing one? https://t.co/jOa0EZRv7Z
DMs open for outreach + securing agent skills.

[AgentSec @agentsec_sh]

Introducing AgentSec — security auditing for AI agent skills with built-in web3 support.

OWASP AST10 covers generic skill risks. Our AST-10 Web3 Annex extends it with 12 onchain-specific rules: signing authority, Permit2 capture, blind signing, RPC pinning, kill-switch, MCP drift, oracle/slippage, key material.

🧵

[AgentSec @agentsec_sh]

We ran the full annex against 11 production DEX router agent skills:

🥇 @odosprotocol 88 B
🥈 SushiSwap 71 C
🥉 CowSwap 70 C
Uniswap 49 D
PancakeSwap 49 D
KyberSwap 49 D
Across 49 D
deBridge 49 D
0x 48 D
https://t.co/3EtF9nVJSA 45 D
1inch 26 F