The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: The skill enables the installation and execution of WASM agents from a community-contributed gallery using the mcp__plugin_ruflo-core_ruflo__wasm_agent_create tool. This allows the execution of code provided by external, potentially untrusted sources.
[INDIRECT_PROMPT_INJECTION]: The skill ingests data from a community gallery that could contain malicious instructions designed to manipulate the agent's behavior.
Ingestion points: Data retrieved from mcp__plugin_ruflo-core_ruflo__wasm_gallery_list and mcp__plugin_ruflo-core_ruflo__wasm_gallery_search in SKILL.md.
Boundary markers: None identified.
Capability inventory: The agent has access to Bash and tools for creating and exporting WASM agents.
Sanitization: No sanitization or validation of the community-sourced content is described.
[COMMAND_EXECUTION]: The skill is granted access to the Bash shell, which provides a high-privilege execution environment.

wasm-gallery