validate-album
Pass
Audited by Gen Agent Trust Hub on Apr 4, 2026
Risk Level: SAFECOMMAND_EXECUTIONDATA_EXFILTRATIONPROMPT_INJECTION
Full Analysis
- [DATA_EXFILTRATION]: The skill accesses a local configuration file at
~/.bitwize-music/config.yamland reads album data from directories defined in thecontent_rootandaudio_root. This access is necessary for the skill's stated purpose of album validation and does not involve sending data to external or untrusted domains. - [COMMAND_EXECUTION]: The skill utilizes the
Bashtool to perform structural checks (e.g.,test -d,test -f,ls). It also generatesmvcommands to suggest fixes for misplaced directories. These commands are localized to the user's music library and are consistent with the skill's utility functions. - [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it ingests and parses the contents of untrusted markdown files within the
tracks/directory. - Ingestion points: Reads all track metadata files located at
{album_path}/tracks/*.mdusing theReadtool. - Boundary markers: None. The skill processes the content of these files without explicit delimiters or instructions to ignore embedded agent commands.
- Capability inventory: The agent has access to
Bashand thebitwize-music-mcptoolset, which can modify the file system. - Sanitization: None. The skill extracts specific fields (Status, Suno Inputs, etc.) but does not sanitize the remaining text for potential instructions.
Audit Metadata