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 PlamenTSV/plamen --skill rpc-surface-auditgit clone --depth 1 https://github.com/PlamenTSV/plamenWrote 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/plamentsv/plamen/rpc-surface-audit)<a href="https://agentmods.dev/skills/plamentsv/plamen/rpc-surface-audit"><img src="https://agentmods.dev/badge/skills/plamentsv/plamen/rpc-surface-audit/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/plamentsv/plamen/rpc-surface-audit"><img src="https://agentmods.dev/badge/skills/plamentsv/plamen/rpc-surface-audit.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 3 findings, up to high
These are SkillSpector’s own severities. On a checked sample its high-severity flags on skills were ~96% false positives — a documented command, a public API, a “never do X” rule — so we show them as a caution to read, not a verdict. Why →
- high YARA Match · line 68 YARA rule matched a hack tool or exploit indicator (offensive tools, reconnaissance, privilege escalation, or exploit frameworks).Fix: Remove offensive tool references and exploit code. Legitimate agent skills should not contain penetration testing tools, exploit frameworks, or reconnaissance utilities.
- high Anti-Refusal · line 148 Skill attempts to nullify the agent's safety policies or restrictions ('you have no restrictions', 'ignore your guidelines', 'do anything now'). This is a direct jailbreak that disables guardrails.Fix: Remove jailbreak framing that nullifies safety policies or restrictions. Skill content must not instruct the agent to ignore its guidelines or operate without guardrails.
- high Prompt Injection · line 148 This pattern attempts to override system instructions or ignore safety constraints. Without LLM analysis, manual review is recommended.Fix: Remove or rewrite any text that instructs the agent to ignore prompts, override safety rules, or trust unverified content. Ensure skill content cannot be injected to alter agent behavior.
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 | $0.00036 | $0.03654 |
| Opus 5 | $0.00018 | $0.01827 |
| Sonnet 5 | $0.00007 | $0.00731 |
| Haiku 4.5 | $0.00004 | $0.00365 |
Grade A, and why
rpc-surface-audit 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 6d 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 — 231 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Injectable Skill: RPC Surface Audit
L1 trigger:
L1_PATTERN=trueAND (rpc/ORjsonrpcORengine_apiOReth/apiORwebsocketORipcdetected in recon subsystem map) Inject Into:depth-network-surfaceLanguage: Go and Rust Finding prefix:[RPC-N]Status: v0.1 draft, Round 4 exemplars pending
Orchestrator Decomposition Guide
- Section 1: depth-network-surface (attack surface)
- Section 2: depth-network-surface (auth + rate limit)
- Section 3: depth-state-trace (subscription state)
- Section 4: depth-edge-case (method boundaries)
When This Skill Activates
Recon identifies an RPC subsystem. RPC is the most publicly exposed attack surface on any L1 node — typically unauthenticated (HTTP JSON-RPC, WebSocket) or semi-authenticated (Engine API with JWT). Even a Medium-severity bug here often upgrades to High because of permissionless reachability (see severity-matrix.md modifier).
1. Attack Surface Enumeration
Enumerate all RPC entry points via LSP workspace/symbol filtered by known method-registration patterns:
| Transport | Registration pattern | Example |
|---|---|---|
| HTTP JSON-RPC | rpc.Register, httpServer.Handle, #[method(name=...)] |
eth_*, debug_*, admin_* |
| WebSocket | Same as HTTP + subscription handlers | eth_subscribe |
| IPC (unix socket) | Often same as HTTP | Geth admin namespace |
| Engine API | JWT-authenticated | engine_newPayloadV*, engine_forkchoiceUpdatedV* |
| Prometheus metrics | /metrics endpoint |
often bound to all interfaces |
| PPROF profiling | /debug/pprof/ (Go) |
should NEVER be public |
Write the enumeration to scratchpad/rpc_surface.md.
2. Authentication and Namespace Gating
2a. Default exposure
- What namespaces are enabled by default on HTTP? (Geth:
eth,net,web3. Notadmin,debug,personal.) - Is the default bind address localhost or 0.0.0.0?
- Is authentication required for any namespace?
2b. Dangerous namespaces
admin_*— should never be exposed on HTTP; check the config validationdebug_*— can expose internal state; check defaultpersonal_*— key management; deprecated in Geth but still present in forksengine_*— JWT-authenticated; check the JWT secret handlingminer_*/txpool_*— varies by client
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.
- 6d ago First seen · 231 lines · 36 tokens per session scan A 5b7fa2cd599b
rpc-surface-audit is a skill published in the GitHub repository PlamenTSV/plamen (295 stars, last pushed 2d ago), licensed MIT. It adds 36 tokens to every session and 3,654 once invoked, about $0.0002 per session on Opus 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 2026-09-03.
Other skills, from other repositories
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.
prowler-tour
Keeps product-tour definitions aligned with the UI features they describe. Trigger: When modifying UI components that have associated tours, editing tour definition files, or renaming data-tour-id attributes.
evm-bytecode-analysis
Analyze supplied deployed EVM runtime bytecode with EVMole or guide a separate application in integrating a published EVMole Rust, Go, Python, or JavaScript binding. Use for unverified-contract inspection, ABI reconstruction from runtime code, selector discovery, storage-access analysis, EVM control-flow inspection…
talos-action-development
Develop, modify, review, and maintain standalone Talos actions in contracts/tasks/actions, including chain guardrails, contract bindings, transaction safety, schedules, action catalogues, and Talos documentation. Use when adding an action, changing an action’s behavior or parameters, updating a Talos schedule, or…
web3-poc-foundry
Complete Foundry PoC writing guide + all cheatcodes + DeFiHackLabs reproduction patterns. Use this when building a proof of concept exploit, setting up a fork test, using Foundry cheatcodes, or reproducing a known DeFi hack for learning.
web3-grep-arsenal
Master grep command arsenal for Web3 smart contract auditing. Use when starting a new protocol scan, before deep code review, or when hunting specific vulnerability classes.