A browsable directory of open source Claude Code plugins
SaferSkills independently audited agent-mart (Agent Skill) and scored it 45/100 (orange). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 8 high-severity and 1 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 9 flagged
A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.A base64 string of 128+ characters appears in a documentation file. Encoded prompt injection hides the hostile instruction in base64 — invisible to keyword filters — and relies on the agent's ability to decode it at runtime. There is no normal authoring reason to embed a multi-hundred-byte base64 blob in skill docs.
*.sig, SIGNATURES) outside the documentation.The text {match} is the classic direct prompt-injection phrasing. Placed in a skill body that the agent reads as trusted instructions, it tries to make the agent abandon its prior rules and follow whatever comes next — a full system-prompt override.
ignore/disregard/forget … previous instructions sentence.The text {match} asks the agent to disclose its hidden system prompt or initial instructions. That is often the first step of a larger attack: knowing the system prompt lets an attacker craft inputs that defeat its constraints by mimicking its own voice.
repeat/reveal/print your system prompt request from the skill.Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
Discover and install Claude Code plugins published on GitHub.
[agentmart.cc](https://agentmart.cc)
<img width="1536" height="688" alt="Agent Mart" src="https://github.com/user-attachments/assets/757896e8-1add-4809-aa98-fdf2b01fced7" />
The home page displays all indexed marketplaces as cards. Each card shows:
Filter state is synced to URL parameters for shareable links.
<img width="1687" height="971" alt="Screenshot 2026-01-30 at 1 50 09 PM" src="https://github.com/user-attachments/assets/5be5d24c-15f6-480e-bbbc-f60551889acb" />
Click any card to view the full marketplace details:
<img width="1689" height="974" alt="Screenshot 2026-01-30 at 1 51 36 PM" src="https://github.com/user-attachments/assets/53d3b6dc-dba4-4d54-8846-6f8b7e398afb" />
Agent Mart crawls GitHub repositories for marketplace.json files and builds a searchable directory. All data comes directly from GitHub - no manual curation or separate database.
agent-mart/
├── src/
│ ├── lib/ # GitHub client, cache, parsers, validators, categorizer
│ └── pipeline/ # 8-step ETL pipeline (01-discover to 09-output)
├── scripts/ # Pipeline orchestrator and visualizer
├── tests/ # ETL unit tests
├── web/public/data/ # Generated JSON output
└── web/ # Next.js frontend applicationFound a bug or have a feature request? Open an issue.
MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.