Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add UnboundCompute/security-agent-skills --skill auditing-cross-chain-bridge-and-message-trustgit clone --depth 1 https://github.com/UnboundCompute/security-agent-skillsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-cross-chain-bridge-and-message-trust)<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-cross-chain-bridge-and-message-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-cross-chain-bridge-and-message-trust/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/unboundcompute/security-agent-skills/auditing-cross-chain-bridge-and-message-trust"><img src="https://agentmods.dev/badge/skills/unboundcompute/security-agent-skills/auditing-cross-chain-bridge-and-message-trust.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00193 | $0.02270 |
| Opus 5.5 | $0.00077 | $0.00908 |
| Sonnet 5.5 | $0.00039 | $0.00454 |
| Haiku 4.5 | $0.00019 | $0.00227 |
Grade A, and why
auditing-cross-chain-bridge-and-message-trust scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 146 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Auditing cross-chain bridge and message trust: the destination must prove the source event, not assume it
A cross-chain bridge does one hard thing: it makes an action on the destination chain, minting a wrapped token, releasing locked funds, running a message, conditional on an event that happened on the source chain. The destination cannot see the source directly, so it trusts a proof or an attestation that the event occurred, and every bridge hack is a failure of that trust. If the destination accepts a mint or release on a forged proof, an unverified claim, or an attestation from a signer set an attacker can spoof or that is too small to be safe, the attacker manufactures value from nothing. If a valid message can be replayed, on the destination twice, or on another chain, one legitimate event authorizes many withdrawals. And the lock-and-mint or burn-and-release accounting that is supposed to keep supply balanced can be pushed out of balance by a message that mints without a matching lock or releases without a matching burn. The audit follows a message from source event to destination action and checks that the destination genuinely verifies the event, binds the message so it executes once, and keeps the accounting balanced. You audit this by crafting messages the destination should reject and seeing whether it mints or releases.
When to use
- A bridge or messaging layer authorizes a destination-chain action (mint, release, call) on the strength of a claimed source-chain event.
- The proof or attestation may be forgeable, or the signer set or validator quorum may be spoofable or too small.
- A cross-chain message may be replayable on the destination or across chains, or the lock/mint accounting may be pushable out of balance.
Scope check
Test bridge and message trust only against protocols and infrastructure you own or are authorized to assess, on testnets or a local fork. Forging messages and triggering mints or releases moves real value, so use test deployments and never mint, release, or unbalance a live bridge or touch funds that are not yours. If you can't name the authorization, stop.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 146 lines · 193 tokens per session scan A ac93cc944dbc
auditing-cross-chain-bridge-and-message-trust is a skill published in the GitHub repository UnboundCompute/security-agent-skills (5 stars, last pushed 1mo ago), licensed MIT. It adds 193 tokens to every session and 2,270 once invoked, about $0.0008 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-05.
Other skills, from other repositories
prodcheck-review
Review this codebase against the prodcheck pre-production checklists — security, performance, scale, integrations, post-launch readiness and people. Use when asked to check whether a project is ready to ship, to audit an area before launch, or to work through a specific checklist. Produces evidence with file:line…
web3-audit
Smart contract security audit — 10 DeFi bug classes (accounting desync, access control, incomplete path, off-by-one, oracle, ERC4626, reentrancy, flash loan, signature replay, proxy), pre-dive kill signals (TVL < $500K etc), Foundry PoC template, grep patterns for each class, and real Immunefi paid examples. Use for…
analyzing-ethereum-smart-contract-vulnerabilities
Perform static and symbolic analysis of Solidity smart contracts using Slither and Mythril to detect reentrancy, integer overflow, access control, and other vulnerability classes before deployment to Ethereum mainnet.
integrate-arcjet-guard-genkit
Integrate Arcjet security into a Genkit JS agent using @arcjet/guard — wrap ai.defineTool, put guardMiddleware on generate({ use }) for unwrapped / MCP / filesystem tools, and read a caller-owned id from generate({ context }). Use when asked to add Arcjet to genkit, rate limit its tools, screen inbound messages, or…
integrate-arcjet-guard-claude-managed-agents
Integrate Arcjet security into Claude Managed Agents (hosted REST+SSE, beta managed-agents-2026-04-01) using @arcjet/guard — screen user.message / initialevents before sessions.events.send, and gate custom tools on agent.customtooluse. Use when asked to add Arcjet to Claude Managed Agents, rate limit custom tools, or…
linear-claude-skill
Manage Linear issues, projects, and teams.