app-icon-generator

Pass

Audited by Gen Agent Trust Hub on Jul 29, 2026

Risk Level: SAFECOMMAND_EXECUTIONREMOTE_CODE_EXECUTIONPROMPT_INJECTION
Full Analysis
  • [COMMAND_EXECUTION]: The skill performs shell command execution to run the generated Swift generator and invoke the system's sips image processing utility.
  • [REMOTE_CODE_EXECUTION]: The skill generates a Swift script (scripts/generate-icon.swift) at runtime and then executes it, which constitutes a dynamic code generation and execution pattern.
  • [PROMPT_INJECTION]: The skill processes untrusted project metadata, creating a surface for indirect prompt injection.
  • Ingestion points: Reads context from .planning/APP.md, .planning/CODEBASE.md, and project files using the Grep tool.
  • Boundary markers: Not present; the instructions do not specify the use of delimiters or 'ignore' instructions when reading external content.
  • Capability inventory: The skill possesses Bash (command execution), Write (file creation), Read, and Edit capabilities.
  • Sanitization: Not present; no explicit validation or escaping of gathered metadata is performed before it influences the script generation logic.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 29, 2026, 02:43 PM
Security Audit — agent-trust-hub — app-icon-generator