The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection through the processing of external lyrics and album concepts.
Ingestion points: Data is fetched via the get_album_full and load_override tools as described in SKILL.md.
Boundary markers: The workflow does not specify the use of delimiters or 'ignore' instructions to isolate ingested content from the generation prompt.
Capability inventory: The skill has permissions to write and edit files in the workspace (using Write, Edit, Glob, Grep) to create the promo/ directory content.
Sanitization: No input validation or sanitization of the lyrics or track concepts is performed before they are used to generate public-facing social media posts.

promo-writer