The Agent Skills Directory

[COMMAND_EXECUTION]: The skill uses the curl utility to interact with the Mem0 API and references a zero doctor command for troubleshooting.
[DATA_EXFILTRATION]: User content and session identifiers are transmitted to api.mem0.ai to enable memory features. The skill also writes request payloads to /tmp/, which could expose data to other processes on the same system.
[PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection by retrieving and processing external memory data without sanitization or boundary markers.
Ingestion points: Memory data enters the agent context through GET /v1/memories/ and POST /v1/memories/search/ endpoints defined in SKILL.md.
Boundary markers: Absent; the instructions do not use delimiters or warnings to separate retrieved memories from system prompts.
Capability inventory: The skill can execute shell commands via curl and manipulate local files.
Sanitization: Absent; content returned from the API is used directly in the agent's logic.

mem0