The Agent Skills Directory

[COMMAND_EXECUTION]: The skill executes shell commands using Bash to interact with the @openant-ai/cli tool for managing task submissions and file uploads.
[EXTERNAL_DOWNLOADS]: The skill utilizes npx to download and execute the @openant-ai/cli package from the NPM registry at runtime.
[DATA_EXFILTRATION]: The skill is designed to upload local files to the vendor's remote storage as part of the submission process. While this is the intended functionality, it creates a mechanism for transferring data from the agent's environment to external infrastructure.
[PROMPT_INJECTION]: The skill has an attack surface for indirect prompt injection because it processes task IDs and file content from the local environment.
Ingestion points: The skill ingests task IDs from the conversation context and identifies file paths for upload based on the agent's work.
Boundary markers: There are no explicit delimiters or instructions provided to the agent to prevent the execution of instructions that might be embedded in the files being uploaded or the task metadata.
Capability inventory: The skill possesses the capability to execute shell commands, perform network uploads, and submit data to the OpenAnt API.
Sanitization: There is no evidence of sanitization or validation performed on the task IDs, file paths, or text descriptions before they are used as arguments for the CLI tool.

submit-work