brightdata-core-workflow-b

Pass

Audited by Gen Agent Trust Hub on Sep 13, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [INDIRECT_PROMPT_INJECTION]: The skill retrieves and processes data from external sources (Google search results and Bright Data datasets) which could contain adversarial content designed to influence the agent's behavior.
  • Ingestion points: Data is ingested via fetch in serp-api.ts and web-scraper-api.ts, and via requests.post in serp_api.py.
  • Boundary markers: No explicit delimiters or instructions to ignore embedded commands are present in the processing logic.
  • Capability inventory: The skill possesses network capabilities (fetch, requests) and file system access (Read, Write, Edit, Bash) which could be targeted by successful injection.
  • Sanitization: The retrieved JSON payloads are logged and returned without explicit validation or sanitization of their text content.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 13, 2026, 01:41 AM
Security Audit — agent-trust-hub — brightdata-core-workflow-b