competition-ios-runtime

Pass

Audited by Gen Agent Trust Hub on Mar 31, 2026

Risk Level: SAFE
Full Analysis
  • [PROMPT_INJECTION]: The skill exhibits an indirect prompt injection surface as it is designed to ingest and process data from external iOS application bundles. This is characteristic of the skill's intended use-case for security research.
  • Ingestion points: Processes Info.plist, entitlements, Keychain data, and runtime hook output (SKILL.md, references/ios-runtime.md).
  • Boundary markers: Absent; the instructions do not specify delimiters for external content.
  • Capability inventory: Focuses on information gathering and runtime analysis of targeted IPAs.
  • Sanitization: Absent; the skill does not instruct the agent to sanitize or validate the content of the analyzed files.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 31, 2026, 12:15 PM