mirror of
https://github.com/agent0ai/agent-zero.git
synced 2026-05-25 06:27:33 +00:00
Calibrate scanner prompts around demonstrated risk instead of the mere presence of common plugin capabilities. Treat scoped credentials, network calls, filesystem access, subprocesses, prompts, and generated assets as expected behavior when they match the declared plugin purpose, while keeping warnings and failures for ambiguity, unsafe handling, concealment, exploitability, or purpose mismatch. Add regression coverage for the rendered scanner prompt so this calibration is preserved. |
||
|---|---|---|
| .. | ||
| main.html | ||
| plugin-scan-checks.json | ||
| plugin-scan-prompt.md | ||
| plugin-scan-store.js | ||
| plugin-scan.html | ||
| thumbnail.jpg | ||