The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill instructions utilize npx @claude-flow/cli@latest to perform memory transfer operations. This involves downloading and executing the latest version of a package from the npm registry.
[PROMPT_INJECTION]: The skill possesses a surface for indirect prompt injection as it is designed to import memory data (RVF files) which could contain adversarial instructions.
Ingestion points: Data enters the system via the mcp__claude-flow__memory_import_claude tool and the hooks transfer from-project command.
Capability inventory: The skill has access to the Bash tool and various memory manipulation tools, providing a path for injected instructions to trigger local command execution.
Sanitization: There are no documented sanitization or validation routines for the content of imported RVF files.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' directives to prevent the agent from obeying instructions embedded within the imported memory data.

rvf-manage