The Agent Skills Directory

[COMMAND_EXECUTION]: The skill utilizes the curl utility within a Bash environment to perform HTTP GET requests to the memory service. This is the primary method for retrieving relevant historical data as described in the skill's purpose.
[DATA_EXFILTRATION]: User-provided search keywords and the MEM9_TENANT_ID identifier are transmitted to the api.mem9.ai endpoint. These transmissions are directed to the vendor's official domain for the purpose of retrieving shared memories and do not represent unauthorized data exfiltration.
[PROMPT_INJECTION]: The skill processes content retrieved from an external service, which creates an indirect injection surface. 1. Ingestion points: Data enters the agent context from the api.mem9.ai memories endpoint. 2. Boundary markers: The instructions lack explicit delimiters or specific warnings to ignore instructions that might be contained within the retrieved memory content. 3. Capability inventory: The skill has authorized access to the Bash tool and curl command. 4. Sanitization: There are no mentioned mechanisms for sanitizing or validating the memory content before the agent summarizes it.

mem9-recall