tailrocks-macos-design

Pass

Audited by Gen Agent Trust Hub on Sep 8, 2026

Risk Level: SAFECOMMAND_EXECUTIONINDIRECT_PROMPT_INJECTIONDYNAMIC_EXECUTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill instructs the agent to execute a vendor-provided local script, bun scripts/macos-design-bless.ts, to record user approval for design prototypes. It also mentions using xcrun swiftc for verifying API availability.\n- [INDIRECT_PROMPT_INJECTION]: The skill processes user-supplied design descriptions and external documentation from Apple. It proactively mitigates injection risks through specific policies in SKILL.md and references/runtime-trust.md that command the agent to treat all such data as non-authoritative evidence.\n- [DYNAMIC_EXECUTION]: The workflow involves the generation and compilation of Swift-based executable prototype packages in the Design/Prototypes/ directory, following structured templates and project baselines.
Audit Metadata
Risk Level
SAFE
Analyzed
Sep 8, 2026, 03:12 PM
Security Audit — agent-trust-hub — tailrocks-macos-design