The Agent Skills Directory

[INDIRECT_PROMPT_INJECTION]: The skill ingests untrusted user input via the $ARGUMENTS variable and saves it directly to a long-term storage tool (memory_save).
Ingestion points: User input is captured via $ARGUMENTS in SKILL.md and passed to the content field of the memory_save tool.
Boundary markers: The instructions lack explicit boundary markers or directives for the agent to treat retrieved memories as non-executable data, increasing the risk that a stored payload could influence future agent behavior during a recall operation.
Capability inventory: While this specific skill only utilizes the memory_save tool, the agent environment typically includes file system access, network operations, and command execution capabilities that could be targeted by successful injection.
Sanitization: There is no evidence of sanitization, validation, or escaping of the user-provided content before it is stored in the long-term memory system.

remember