unity-cloud-build

Pass

Audited by Gen Agent Trust Hub on Apr 2, 2026

Risk Level: SAFEEXTERNAL_DOWNLOADSCOMMAND_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [EXTERNAL_DOWNLOADS]: Fetches the @membranehq/cli tool from the official npm registry, which is the vendor's authorized package for platform interaction.\n- [COMMAND_EXECUTION]: Executes standard membrane CLI commands to manage connections and run actions as part of the intended integration workflow.\n- [PROMPT_INJECTION]: The skill has an indirect prompt injection surface as it processes external data from Unity Cloud Build.\n
  • Ingestion points: Data enters the agent context through membrane action list, membrane action run, and membrane request commands in SKILL.md.\n
  • Boundary markers: None identified in the provided instructions.\n
  • Capability inventory: The agent can execute shell commands using the membrane CLI as described in SKILL.md.\n
  • Sanitization: No explicit sanitization or validation of the external API responses is described.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 2, 2026, 04:10 PM