skills/brightdata/skills/search/Gen Agent Trust Hub

search

Pass

Audited by Gen Agent Trust Hub on Oct 29, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted data from search engines and web pages, which could contain malicious instructions designed to influence the agent's behavior.
  • Ingestion points: Results from bdata search and bdata discover commands, as well as full page content when the --include-content flag is used (detailed in SKILL.md and references/examples.md).
  • Boundary markers: While the skill expects structured JSON output and uses jq for parsing, it lacks explicit instructions for the agent to ignore or isolate instructions potentially embedded within the retrieved search results or page bodies.
  • Capability inventory: The skill utilizes file system writing (-o flag), network communication (via the bdata CLI and curl), and shell command execution (xargs with bash -c).
  • Sanitization: A legacy curl fallback example in references/patterns.md uses jq -sRr @uri to sanitize search queries, but there is no evidence of sanitization for the content retrieved from external pages before it is processed by the agent.
  • [COMMAND_EXECUTION]: The skill relies on the bdata CLI tool and various shell utilities to execute its functions, involving complex command pipelines.
  • Evidence: Batch processing patterns in references/patterns.md use xargs combined with bash -c to execute scraping tasks for multiple URLs in parallel.
  • The instructions provide patterns for shell loops that handle user-provided queries or data from external files (queries.txt), which are then passed as arguments to CLI commands.
Audit Metadata
Risk Level
SAFE
Analyzed
Oct 29, 2026, 04:30 PM