competitive-intel

Fail

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: HIGHREMOTE_CODE_EXECUTIONCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [REMOTE_CODE_EXECUTION]: The skill requires the installation of the Bright Data CLI using a shell-piped script: curl -fsSL https://cli.brightdata.com/install.sh | bash. While this is the official installation method for the vendor's software, it executes a remote script directly in the environment.
  • [COMMAND_EXECUTION]: Extensive use of shell commands through the bdata CLI to perform data collection, including searches, scraping, and pipeline execution.
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted data from arbitrary external websites. 1. Ingestion points: Content retrieved via bdata scrape and structured pipelines. 2. Boundary markers: The instructions do not provide specific delimiters or ignore-instructions to isolate the agent from content in the scraped data. 3. Capability inventory: The agent has access to a shell for executing bdata commands and potentially other operations. 4. Sanitization: No explicit validation or filtering of retrieved web content is performed before analysis.
Recommendations
  • HIGH: Downloads and executes remote code from: https://cli.brightdata.com/install.sh - DO NOT USE without thorough review
Audit Metadata
Risk Level
HIGH
Analyzed
Mar 31, 2026, 01:43 PM