The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to execute a local shell script 'scripts/moa/run.sh' to orchestrate model queries and synthesize answers.
[DATA_EXFILTRATION]: The skill is designed to send user prompts to external model provider APIs or gateways. This requires network operations and the management of provider API keys.
[PROMPT_INJECTION]: The skill exhibits an attack surface for indirect prompt injection through its core functionality of synthesizing multiple model responses. 1. Ingestion points: Untrusted user prompts are passed as arguments to the 'scripts/moa/run.sh' script. 2. Boundary markers: The skill does not define specific delimiters or instructions to prevent the agent from following instructions embedded within the user-supplied prompts. 3. Capability inventory: The skill utilizes shell execution and network access to communicate with multiple external APIs. 4. Sanitization: No input sanitization or filtering logic is described in the provided skill documentation.

moa