The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill utilizes npx to download and execute the @openant-ai/cli package. This is a verified vendor resource belonging to 'openant-ai'.
[COMMAND_EXECUTION]: Commands are executed via the Bash tool to interact with the OpenAnt platform CLI.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it retrieves and processes untrusted user-generated content from the platform, such as task descriptions and tags. 1. Ingestion points: Task data is ingested through the tasks list and tasks get commands in SKILL.md. 2. Boundary markers: None provided; the agent is not instructed to treat retrieved task fields as untrusted or to ignore embedded instructions. 3. Capability inventory: The agent has the ability to execute Bash commands for CLI operations. 4. Sanitization: There is no mention of sanitizing or validating the contents of task fields before they are returned to the agent context.

search-tasks