Skills
skills/brightdata/brightdata-plugin/search/Gen Agent Trust Hub

search

Pass

Audited by Gen Agent Trust Hub on Apr 19, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The scripts/search.sh script executes curl and jq for API interaction and JSON processing, which are standard utilities for these tasks.
  • [DATA_EXFILTRATION]: The skill performs network requests to api.brightdata.com, the official API endpoint for the vendor, to retrieve search results.
  • [PROMPT_INJECTION]: The skill presents an indirect prompt injection surface as it ingests untrusted search data. (1) Ingestion points: search results via scripts/search.sh. (2) Boundary markers: data is returned as structured JSON. (3) Capability inventory: limited to curl and jq for data retrieval. (4) Sanitization: jq is used to strictly filter and map specific fields from the API response.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 19, 2026, 04:13 PM
Security Audit — agent-trust-hub — search