mobile-dotnet-maui

Pass

Audited by Gen Agent Trust Hub on Jul 8, 2026

Risk Level: SAFEPROMPT_INJECTIONCOMMAND_EXECUTION
Full Analysis
  • [PROMPT_INJECTION]: The skill presents an attack surface for indirect prompt injection as it ingests untrusted user requirements for code generation.
  • Ingestion points: User-provided instructions regarding pages, navigation structure, and data models enter the agent context through SKILL.md.
  • Boundary markers: Absent. No delimiters are used to isolate user content from system instructions.
  • Capability inventory: The skill permits the execution of shell commands (dotnet build, java -jar, security), file system writes, and dependency management across various scripts mentioned in SKILL.md.
  • Sanitization: Absent. The skill does not implement validation or escaping for the processed data.
  • [COMMAND_EXECUTION]: The skill provides patterns for executing shell commands within build and deployment workflows.
  • Evidence: SKILL.md includes examples for Android app signing (dotnet build), iOS keychain management (security create-keychain, security import), and application publication.
Audit Metadata
Risk Level
SAFE
Analyzed
Jul 8, 2026, 12:25 PM
Security Audit — agent-trust-hub — mobile-dotnet-maui