The Agent Skills Directory

[COMMAND_EXECUTION]: The skill instructs the agent to use npx to execute commands via the Notis CLI for all operations, including app development and tool management.
[EXTERNAL_DOWNLOADS]: The skill facilitates the download of the @notis_ai/cli package from the public npm registry using npx. These are vendor-owned resources and are standard for this skill's purpose.
[REMOTE_CODE_EXECUTION]: The notis tools exec and exec-parallel commands allow the agent to run capabilities from external MCP, Composio, and native Notis toolkits.
[INDIRECT_PROMPT_INJECTION]: The skill processes data from external tool outputs and search results, which creates a potential surface for indirect prompt injection.
Ingestion points: Data enters the agent's context through the output of notis tools search, notis tools describe, and notis tools exec as described in SKILL.md.
Boundary markers: The instructions do not specify the use of delimiters or 'ignore' instructions for processing tool output.
Capability inventory: The skill has the capability to execute shell commands via npx and perform network operations via the CLI's API interactions.
Sanitization: While the skill recommends --dry-run and --get-schema to validate tool arguments, it does not provide mechanisms to sanitize natural language instructions within tool outputs.

notis-cli