The Agent Skills Directory

[PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface because it reads and processes data from external project files to generate new content or enrich existing portfolio entities.
Ingestion points: The skill ingests data from multiple JSON files located in the portfolio/ and tips/ directories (e.g., tips-value-model.json, portfolio.json, and market customer files).
Boundary markers: The instructions do not specify the use of delimiters or protective markers (e.g., "ignore embedded instructions") when the agent interpolates source text into generated propositions or evidence.
Capability inventory: The skill possesses the ability to read, write, and edit files within the project environment using the Read, Write, Edit, Glob, and Grep tools.
Sanitization: There is no evidence of explicit sanitization or validation of input strings read from project files before they are utilized for content generation or modification.

trends-bridge