The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill possesses a vulnerability surface for indirect prompt injection by ingesting untrusted data from local files or vault search results. \n
Ingestion points: The skill reads external content from file paths or search results using the Read tool as described in the Process section. \n
Boundary markers: The instructions do not define delimiters or explicit rules to disregard embedded instructions within the processed notes. \n
Capability inventory: The skill utilizes the Read, Edit, Glob, and Grep tools, allowing it to modify files based on its analysis. \n
Sanitization: The skill lacks specific sanitization or validation logic for the content it reads before processing it for flashcard generation.

flashcards