Skip to content

Add Prism Scanner to Ecosystem Tools section #609

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
aidongise-cell wants to merge 1 commit into from
Closed

Add Prism Scanner to Ecosystem Tools section #609

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 17 additions & 0 deletions README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -494,6 +494,23 @@ Use `/security-scan` in Claude Code to run it, or add to CI with the [GitHub Act

[GitHub](https://github.com/affaan-m/agentshield) | [npm](https://www.npmjs.com/package/ecc-agentshield)

### Prism Scanner — Agent Supply Chain Security

Open-source security scanner for AI Agent skills, plugins, and MCP servers. Complements AgentShield (which focuses on your local Claude Code config) by scanning third-party code *before* you install it.

```bash
pip install prism-scanner
prism scan https://github.com/user/some-skill
```

**What it scans:** Agent skills, plugins, and MCP servers across ClawHub, npm, and pip with 39+ detection rules — AST-level taint tracking, malicious signature matching, metadata analysis, and post-uninstall system residue detection.
Copy link
Copy Markdown
Contributor

@greptile-apps greptile-apps bot Mar 18, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Unverified "ClawHub" platform reference

The description mentions ClawHub as a platform Prism Scanner indexes, alongside npm and pip. ClawHub does not appear to be a widely-known or publicly documented platform in the AI-agent/MCP ecosystem. Including it in marketing copy alongside established registries (npm, pip) without a link or explanation may confuse readers or overstate the tool's coverage.

Consider either linking to the ClawHub platform (e.g. [ClawHub](https://clawhub.io)) or removing the reference if it is a placeholder / under-development registry.

Suggested change
**What it scans:** Agent skills, plugins, and MCP servers across ClawHub, npm, and pip with 39+ detection rules — AST-level taint tracking, malicious signature matching, metadata analysis, and post-uninstall system residue detection.
**What it scans:** Agent skills, plugins, and MCP servers across npm and pip with 39+ detection rules — AST-level taint tracking, malicious signature matching, metadata analysis, and post-uninstall system residue detection.


**Grading:** A-F letter grades with severity breakdown and actionable recommendations.

**Output formats:** Terminal, JSON, HTML, SARIF (GitHub Code Scanning integration).

[GitHub](https://github.com/aidongise-cell/prism-scanner) | [PyPI](https://pypi.org/project/prism-scanner/) | [MCP Server](https://mcp.so/server/prism-scanner)
Copy link
Copy Markdown
Contributor

@cubic-dev-ai cubic-dev-ai bot Mar 18, 2026 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2: User-facing docs now instruct users to install/run an external tool from an unvetted third-party repo/package, which violates the team policy to avoid linking to unapproved external repositories in docs (supply-chain risk).

Prompt for AI agents 
Check if this issue is valid — if so, understand the root cause and fix it. At README.md, line 512:

<comment>User-facing docs now instruct users to install/run an external tool from an unvetted third-party repo/package, which violates the team policy to avoid linking to unapproved external repositories in docs (supply-chain risk).</comment>

<file context>
@@ -494,6 +494,23 @@ Use `/security-scan` in Claude Code to run it, or add to CI with the [GitHub Act
+
+**Output formats:** Terminal, JSON, HTML, SARIF (GitHub Code Scanning integration).
+
+[GitHub](https://github.com/aidongise-cell/prism-scanner) | [PyPI](https://pypi.org/project/prism-scanner/) | [MCP Server](https://mcp.so/server/prism-scanner)
+
 ### 🔬 Plankton — Write-Time Code Quality Enforcement
</file context>
Fix with Cubic


Comment on lines +499 to +513
Copy link
Copy Markdown
Contributor

@coderabbitai coderabbitai bot Mar 18, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

⚠️ Potential issue | 🟡 Minor

Add the Prism Scanner license to match the documented PR intent.

The new block omits the license detail (Apache 2.0), which is useful trust/compliance context for security tooling.

✏️ Proposed docs patch 
 Open-source security scanner for AI Agent skills, plugins, and MCP servers. Complements AgentShield (which focuses on your local Claude Code config) by scanning third-party code *before* you install it.
+License: Apache 2.0.
🤖 Prompt for AI Agents 
Verify each finding against the current code and only fix it if needed.

In `@README.md` around lines 499 - 513, Add the Apache-2.0 license information to
the README for prism-scanner: insert an SPDX short identifier and a visible
license badge and a short "License" section (mentioning Apache License 2.0 with
a link to the full text) near the project title/links, and ensure the README
references the same Apache-2.0 wording shown in the repository (so README.md,
the prism-scanner project name, and the existing GitHub/PyPI links reflect the
licensed status).

### 🔬 Plankton — Write-Time Code Quality Enforcement

Plankton (credit: @alxfazio) is a recommended companion for write-time code quality enforcement. It runs formatters and 20+ linters on every file edit via PostToolUse hooks, then spawns Claude subprocesses (routed to Haiku/Sonnet/Opus by violation complexity) to fix issues the main agent missed. Three-phase architecture: auto-format silently (40-50% of issues), collect remaining violations as structured JSON, delegate fixes to a subprocess. Includes config protection hooks that prevent agents from modifying linter configs to pass instead of fixing code. Supports Python, TypeScript, Shell, YAML, JSON, TOML, Markdown, and Dockerfile. Use alongside AgentShield for security + quality coverage. See `skills/plankton-code-quality/` for full integration guide.
Expand Down