album-dashboard
Pass
Audited by Gen Agent Trust Hub on Sep 14, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted external data which could contain malicious instructions designed to influence the agent's behavior.
- Ingestion points: The skill ingests data from the
bitwize-music-mcpserver tools (get_album_progress,find_album,list_track_files) which return album metadata, track lists, and per-track fields. It also processes content fromREADME.md,RESEARCH.md,SOURCES.md, and track lyrics. - Boundary markers: The instructions do not define clear delimiters or "ignore embedded instructions" warnings for the external content being processed.
- Capability inventory: The skill uses
Read,Glob, andGreptools to interact with the file system based on the processed metadata. - Sanitization: No explicit sanitization or validation of the ingested content is described before it is used to generate the dashboard report.
Audit Metadata