amazon-research

Pass

Audited by Gen Agent Trust Hub on Aug 10, 2026

Risk Level: SAFE
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill makes network requests to https://api.crawlora.net, which is the official API endpoint for the skill author's service (crawlora-org). These requests are part of the skill's primary functionality for searching Amazon data.
  • [COMMAND_EXECUTION]: The scripts/crawlora.sh script executes curl to interact with the API. It uses standard bash practices (set -euo pipefail) and includes proper URL encoding via curl -G --data-urlencode to prevent command injection from user-supplied parameters.
  • [CREDENTIALS_UNSAFE]: The skill follows security best practices by requiring the API key to be provided via an environment variable (CRAWLORA_API_KEY) rather than hardcoding it. It explicitly warns against committing or hardcoding secrets in the documentation.
  • [DATA_EXFILTRATION]: No sensitive local data is accessed or transmitted. The skill only transmits user-provided search queries to the designated vendor API.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 10, 2026, 06:52 PM
Security Audit — agent-trust-hub — amazon-research