oldnavy-research
Pass
Audited by Gen Agent Trust Hub on Aug 14, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: The skill uses the
CRAWLORA_API_KEYenvironment variable for authentication, which is a standard and secure practice for managing secrets in agent skills, avoiding hardcoded credentials. - [SAFE]: All network operations are performed via
scripts/crawlora.shtargetingapi.crawlora.net, which is the official API endpoint for the vendor 'crawlora-org'. This is consistent with the skill's stated purpose. - [SAFE]: The shell script
scripts/crawlora.shis a minimal wrapper aroundcurlthat usesset -euo pipefailand properly quotes variables to prevent command injection. It correctly uses--data-urlencodefor GET parameters to handle special characters safely. - [SAFE]: No obfuscation, persistence mechanisms, privilege escalation, or prompt injection patterns were found in the instructions or scripts.
Audit Metadata