The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill processes external data that could potentially contain malicious instructions intended to influence agent behavior.
- Ingestion points: The agent reads external configuration from {overrides}/album-art-preferences.md (via the load_override function) and ingests album concepts, tracklists, and themes from the project environment.
- Boundary markers: There are no defined delimiters or instructions to treat external data as untrusted content, increasing the risk that the model might interpret embedded instructions as its own commands.
- Capability inventory: The skill has significant file system capabilities (Read, Edit, Write, Grep, Glob) and access to the bitwize-music-mcp tool, which could be misused if a prompt injection attack is successful.
- Sanitization: The instructions do not define any validation, filtering, or escaping protocols for the ingested data before it is processed.

album-art-director