apptweak

Pass

Audited by Gen Agent Trust Hub on Mar 4, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: The skill recommends installing the @membranehq/cli tool from the npm registry, which is the official CLI for the vendor's platform.
  • [COMMAND_EXECUTION]: The skill utilizes shell commands via the membrane CLI to manage connections, list actions, and execute API requests.
  • [PROMPT_INJECTION]: The skill processes external data from app stores, including keywords and app reviews, which creates a surface for indirect prompt injection.
  • Ingestion points: App reviews and keyword metadata fetched via CLI actions or proxy requests as described in SKILL.md.
  • Boundary markers: No delimiters or instruction-bypass warnings are mentioned for the external content.
  • Capability inventory: The agent is capable of executing shell commands through the CLI and making network requests.
  • Sanitization: No explicit sanitization or content validation steps are documented for the retrieved data.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 4, 2026, 08:56 AM