The Agent Skills Directory

[PROMPT_INJECTION]: The skill processes untrusted data from the conversation history and uses it to update persistent files, including its own SKILL.md instructions.- Ingestion points: Extracts information from the 'recent conversation context' as described in SKILL.md.- Boundary markers: No explicit delimiters or instructions to ignore embedded commands within the conversation context are defined.- Capability inventory: The skill is authorized to update files, including its own SKILL.md or project checklists, based on the processed content.- Sanitization: No validation or sanitization of the extracted content before writing to files is specified in the instructions.

lesson