parallel-cli
Fail
Audited by Gen Agent Trust Hub on Oct 2, 2026
Risk Level: CRITICALREMOTE_CODE_EXECUTIONINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
- [REMOTE_CODE_EXECUTION]: The skill instructs the user to execute a command that pipes a remote script directly to the shell:
curl -fsSL https://parallel.ai/install.sh | bash. This pattern allows an external server to run arbitrary code on the host system without any verification or integrity checks. - [COMMAND_EXECUTION]: The skill requires the execution of multiple system commands and package managers (
brew,npm,pip,pipx) to install and operate theparallel-clitool. - [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted data from the web, which creates a significant attack surface for indirect prompt injection.
- Ingestion points: Data retrieved from external websites via the
search,extract, andresearchcommands inSKILL.md. - Boundary markers: The instructions do not define any delimiters or safety warnings to separate external content from the agent's internal reasoning.
- Capability inventory: The skill has the ability to execute CLI commands and write output to the local file system (e.g., to
/tmp/). - Sanitization: There are no instructions to sanitize, escape, or validate the content retrieved from external sources before the agent processes it.
Recommendations
- HIGH: Downloads and executes remote code from: https://parallel.ai/install.sh - DO NOT USE without thorough review
- AI detected serious security threats
Audit Metadata