macos-menubar-tuist-app

Pass

Audited by Gen Agent Trust Hub on Sep 15, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to perform local build and process management tasks using tuist and shell scripts (run-menubar.sh, stop-menubar.sh). It also suggests using curl to probe backend endpoints. These operations are standard for a developer-oriented skill focused on macOS app lifecycle management.
  • [INDIRECT_PROMPT_INJECTION]: The skill has a vulnerability surface where it ingests external data from backend endpoints via curl to verify API structure.
  • Ingestion points: Workflow step 2 mentions using curl to verify endpoint shapes and response mapping.
  • Boundary markers: None identified for external data processing.
  • Capability inventory: The skill has the ability to execute shell commands (bash), build tools (tuist), and network commands (curl).
  • Sanitization: No specific sanitization or validation of the ingested API data is described beyond architectural decoding logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 15, 2026, 03:25 PM
Security Audit — agent-trust-hub — macos-menubar-tuist-app