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 trilwu/secskills --skill attacking-grpc-protobufgit clone --depth 1 https://github.com/trilwu/secskillsWrote 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/trilwu/secskills/attacking-grpc-protobuf)<a href="https://agentmods.dev/skills/trilwu/secskills/attacking-grpc-protobuf"><img src="https://agentmods.dev/badge/skills/trilwu/secskills/attacking-grpc-protobuf/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/trilwu/secskills/attacking-grpc-protobuf"><img src="https://agentmods.dev/badge/skills/trilwu/secskills/attacking-grpc-protobuf.svg" alt="Reviewed on agentmods" width="80" height="20"></a>- NVIDIA SkillSpector warn
SkillSpector: 4 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 Prompt Injection · line 191 Hidden instructions were detected in comments or invisible text. These could contain malicious directives. Manual review is recommended.Fix: Audit all comments and invisible characters. Remove any instructions that direct the agent to perform unauthorized actions. Use plain, reviewable content.
- medium Data Exfiltration · line 89 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 146 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
- medium Data Exfiltration · line 160 Data is being sent to an external URL. This could be legitimate telemetry or data exfiltration. Manual review is recommended.Fix: Verify the destination URL is trusted and necessary. Remove or replace with documented APIs. Ensure no secrets, tokens, or PII are transmitted.
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 | $0.00087 | $0.02159 |
| Opus 5 | $0.00044 | $0.01079 |
| Sonnet 5 | $0.00017 | $0.00432 |
| Haiku 4.5 | $0.00009 | $0.00216 |
Grade B, and why
attacking-grpc-protobuf scanned grade B with 1 finding 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 7d 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.
Sends data to an external URLmediumData exfiltration
A POST to an outside endpoint may be telemetry or may be exfiltration; either way the mod talks to somewhere, and you should know where.
grpcurl -plaintext -d '{"user_id": 1}' target:50051 package.Service/GetUser How it starts
The opening of the file, as written. The whole thing — 214 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Attacking gRPC and Protobuf Services
gRPC breaks the tooling assumption that a request is readable text over HTTP/1.1. Burp shows a binary blob or nothing at all, and without the schema you cannot even name the methods. Recover the schema and it becomes an ordinary API test — with the twist that gRPC services are frequently internal services newly exposed, which means their authorization is often weaker than the REST API in front of them.
When to Use
- Traffic uses HTTP/2 with
content-type: application/grpc - A request or response body is opaque binary with no JSON structure
- The app is a mobile or desktop client talking to a backend over protobuf
- You find
.protofiles,*_pb2.py,*.pb.go, orgrpcin a codebase application/grpc-weborapplication/grpc-web+protoappears in a browser app
When NOT to Use
- REST or GraphQL — use
testing-apis - The proxy cannot see the traffic at all on mobile — use
bypassing-mobile-pinning; gRPC clients often ignore system proxy settings - Source code is available — use
auditing-code-for-vulnerabilities, and read the.protofiles directly - Binary protocol that is not protobuf — use
analyzing-binaries
Recover the Schema
Everything depends on this. Four routes, in order of cost.
1. Server reflection. Many services ship it enabled, often unintentionally.
grpcurl -plaintext target:50051 list
grpcurl -plaintext target:50051 list package.ServiceName
grpcurl -plaintext target:50051 describe package.ServiceName.MethodName
grpcurl -plaintext target:50051 describe package.RequestMessage
# TLS
grpcurl target:443 list
grpcurl -insecure target:443 list # self-signed / proxy in path
Reflection enabled on an internet-facing service is itself worth reporting — it is the gRPC equivalent of GraphQL introspection in production.
2. Descriptors compiled into a client. Protobuf embeds a serialized
FileDescriptorProto in generated code, so the schema is recoverable from any
client binary.
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.
- 7d ago First seen · 214 lines · 87 tokens per session scan B 0be73e0af435
attacking-grpc-protobuf is a skill published in the GitHub repository trilwu/secskills (138 stars, last pushed 6d ago), licensed MIT. It adds 87 tokens to every session and 2,159 once invoked, about $0.0004 per session on Opus 5. A static security scan graded it B with 1 finding (sends data to an external url). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other skills, from other repositories
build-mcp-server
This skill should be used when the user asks to "build an MCP server", "create an MCP", "make an MCP integration", "wrap an API for Claude", "expose tools to Claude", "make an MCP app", or discusses building something with the Model Context Protocol. It is the entry point for MCP server development — it interrogates…
data-manager-api-setup
Guides developers through client library installation and authentication setup steps for the Data Manager API. Use this skill when a user is getting started with the Data Manager API and needs to setup their local environment, install the client library, or setup access to the API. Don't use for implementing audience…
workers-best-practices
Cloudflare Workers best practices for production applications. Use when writing, reviewing, or configuring Workers.
new
Create a new project to start development quickly.
skd-edit
A focused editor for 1C data composition schemas, the report definitions that describe queries, fields, filters, totals, and parameters. It changes an existing Template.xml file through specific operations.
skd-info
A structure reader for 1C data composition schemas, the report definitions that contain queries, fields, parameters, and display variants. It gives a compact summary instead of requiring you to read the raw XML.