The Agent Skills Directory

[REMOTE_CODE_EXECUTION]: Provides instructions for the agent to download and execute an installation script from the vendor's official domain (https://dist.ota.run/install.sh) by piping it directly to the shell. This is the documented installation path for the Ota CLI.
[EXTERNAL_DOWNLOADS]: Fetches installation scripts and configuration references from the vendor's infrastructure (ota.run) and official GitHub repositories (github.com/ota-run/).
[COMMAND_EXECUTION]: Instructs the agent to run various Ota-specific CLI commands, including ota doctor, ota run, and ota up, which can execute repository-defined tasks and manage system dependencies.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests untrusted data from the local repository to analyze and model contracts.
Ingestion points: Reads repository manifest files including ota.yaml, package.json, README.md, lockfiles, and CI workflow files in SKILL.md.
Boundary markers: Absent. The instructions do not define specific delimiters or warnings to ignore commands embedded in the processed files.
Capability inventory: The agent is authorized to execute shell commands via the ota binary, including named tasks and dependency hydration steps.
Sanitization: Absent. Content read from the repository is processed without validation or structural filtering.

ota