aidongise-cell/Prism Scanner
Security scanner for AI Agent skills, plugins, and MCP servers. 39+ detection rules with AST taint tracking and A-F grading.
View on GitHubTrust Signals
- Scorecard Score
- not yet scored
- Maintenance Recency
- Activelast commit Apr 7, 2026
- License
- Apache 2.0
Pinned Snippet
uses: aidongise-cell/prism-scanner@03ac502f61e2ef094a9b779820c946d4fd7935e8 # v0.2.2tags can be moved; commit SHAs can't. why a SHA?
Inputs
| name | description | required | default |
|---|---|---|---|
| path | Path to scan (default: current directory) | no | . |
| format | Output format: cli, json, sarif, html | no | sarif |
| output-file | Output file path (default: prism-results.sarif for sarif format) | no | prism-results.sarif |
| fail-on | Fail if findings at this severity or above: critical, high, medium | no | "" |
| platform | Force platform type: clawhub, mcp, npm, pip (auto-detected if omitted) | no | "" |
| python-version | Python version to use | no | 3.12 |
| upload-sarif | Upload SARIF results to GitHub Code Scanning (requires security-events: write) | no | true |
Outputs
| name | description |
|---|---|
| grade | Security grade (A-F) |
| findings-count | Number of active findings |
| report-file | Path to the output report file |
| badge | Markdown badge for the scan grade |