apple-app-store-reviews

Pass

Audited by Gen Agent Trust Hub on Aug 7, 2026

Risk Level: SAFE
Full Analysis
  • [COMMAND_EXECUTION]: The skill uses a bash script (scripts/get_apple_reviews.sh) to perform network requests and data processing. The script correctly uses set -euo pipefail for error handling.
  • [EXTERNAL_DOWNLOADS]: The skill makes a network request to ai-factory.frevana.com to fetch app reviews. This is the primary function of the skill and uses a vendor-specific domain consistent with the skill's purpose.
  • [CREDENTIALS_UNSAFE]: The skill manages a FREVANA_TOKEN for authentication. The script is designed to read this from the environment or a command-line flag and explicitly instructs the agent not to echo the token back to the user.
  • [DATA_EXFILTRATION]: While the skill communicates with an external API, it only sends user-provided product IDs and pagination parameters. No sensitive local data (like SSH keys or AWS credentials) is accessed or transmitted.
  • [DYNAMIC_EXECUTION]: The script uses python3 to safely handle JSON serialization and validation. The Python code is passed via stdin (heredoc), which is a standard pattern for small utility tasks in shell scripts and does not involve executing untrusted user input as code.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 7, 2026, 09:57 AM
Security Audit — agent-trust-hub — apple-app-store-reviews