pv-tool
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The application has a surface for ingesting untrusted data through the import of LRC/SRT subtitle files and track metadata/lyrics from a local 'Now Playing' service.
- Ingestion points: Untrusted data enters the agent context through the file upload for LRC/SRT files in
app/src/main.tsand via the WebSocket/Fetch connections to the local 'Now Playing' service inapp/src/core/nowPlayingProvider.ts. - Boundary markers: Absent. The external text is interpolated directly into rendering components and UI text areas without delimiters or 'ignore' instructions.
- Capability inventory: The skill possesses the capability to execute shell commands through the provided management scripts (
scripts/dev.sh,scripts/build.sh, etc.) and perform local network operations. - Sanitization: Absent. Content is processed as raw text for visual rendering on the canvas and display in the UI.
Audit Metadata