Skills
skills/parallel-web/agent-skills/parallel-data-enrichment/Gen Agent Trust Hub

parallel-data-enrichment

Pass

Audited by Gen Agent Trust Hub on Mar 19, 2026

Risk Level: SAFEREMOTE_CODE_EXECUTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill includes an installation command curl -fsSL https://parallel.ai/install.sh | bash. This executes a shell script hosted on the vendor's official domain to set up the environment.
  • [EXTERNAL_DOWNLOADS]: The skill provides an alternative installation method using pipx install "parallel-web-tools[cli]". This fetches the vendor's official package from a public registry.
  • [COMMAND_EXECUTION]: The skill uses the Bash tool to run parallel-cli enrich run and parallel-cli enrich poll commands for processing data.
  • [PROMPT_INJECTION]: The skill processes untrusted external data during the enrichment process.
  • Ingestion points: CSV files (e.g., input.csv) and inline JSON data provided by the user.
  • Boundary markers: None specified in the prompt instructions.
  • Capability inventory: The skill can execute subprocesses via the parallel-cli tool.
  • Sanitization: No explicit sanitization or validation of the input data is mentioned.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 19, 2026, 01:01 AM