The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill uses the npx utility to download the @claude-flow/cli package from the NPM registry during command execution.
[REMOTE_CODE_EXECUTION]: Packages downloaded via npx are executed as code on the host environment.
[COMMAND_EXECUTION]: The skill relies on shell scripts (scripts/memory-backup.sh, scripts/memory-consolidate.sh) to automate CLI tasks and system operations.
[PROMPT_INJECTION]: The skill exhibits a vulnerability surface for indirect prompt injection.
Ingestion points: External or untrusted data can be stored in the memory system using the memory store command and retrieved via memory search as seen in SKILL.md.
Boundary markers: The skill does not implement delimiters or specific instructions to prevent the agent from following commands that might be embedded in the stored data.
Capability inventory: The skill can execute subprocesses and perform file-system writes via the CLI tool in SKILL.md and the associated shell scripts.
Sanitization: No sanitization or validation logic is present to filter or escape content stored in the memory system.

memory-management