The Agent Skills Directory

[EXTERNAL_DOWNLOADS]: The skill fetches an installation script from https://parallel.ai/install.sh and a Python package parallel-web-tools via pipx. These resources are hosted on the vendor's own infrastructure.
[REMOTE_CODE_EXECUTION]: The setup instructions include a pattern where a remote script is downloaded and executed directly by the shell using curl -fsSL https://parallel.ai/install.sh | bash. This is intended for the installation of the vendor's CLI tool.
[COMMAND_EXECUTION]: The skill utilizes the Bash tool to execute parallel-cli for search operations and to run shell commands for environment setup, including pipx install and export for API key management.
[PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it ingests and processes untrusted data from the web.
Ingestion points: Data enters the context from the parallel-cli search command, which retrieves content from external websites (SKILL.md).
Boundary markers: Absent; there are no delimiters or instructions to the agent to disregard instructions potentially embedded within the search results.
Capability inventory: The skill has access to the Bash tool, which is used for CLI execution and file writing (SKILL.md).
Sanitization: The skill does not implement sanitization or validation of the search results before they are processed by the agent.

parallel-web-search