hig-project-context

Pass

Audited by Gen Agent Trust Hub on Apr 21, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection by instructing the agent to ingest and process data from untrusted external project files.\n
  • Ingestion points: Data is gathered from README.md, Package.swift, .xcodeproj, Info.plist, source code, and Assets.xcassets.\n
  • Boundary markers: Absent. The skill does not define specific delimiters or instructions to the agent to ignore or isolate potentially malicious instructions found within the processed files.\n
  • Capability inventory: The skill utilizes file system read capabilities across the project directory and file system write capabilities to create the .claude/apple-design-context.md file.\n
  • Sanitization: Absent. There are no instructions provided to sanitize or validate the content extracted from the project files before it is used to generate the context document.
Audit Metadata
Risk Level
SAFE
Analyzed
Apr 21, 2026, 03:26 AM
Security Audit — agent-trust-hub — hig-project-context