ios-app-development

Pass

Audited by Gen Agent Trust Hub on Aug 3, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill follows security-conscious development practices, explicitly instructing the agent to never print tokens, private keys, or account credentials and to use approved secret management systems.\n- [SAFE]: It utilizes standard, well-known iOS development tools such as xcodebuild, xcrun, and codesign for building and signing applications.\n- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection.\n
  • Ingestion points: The agent reads untrusted data from local specifications and repository instructions (SKILL.md, references/project-foundation.md).\n
  • Boundary markers: None are present to distinguish between instructions and data.\n
  • Capability inventory: The skill has capabilities to write files, perform git operations, and execute build/signing commands (xcodebuild, xcodegen).\n
  • Sanitization: No sanitization or validation of external content is performed before processing. This represents a potential vulnerability if malicious instructions are present in the project requirements.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 3, 2026, 05:28 AM
Security Audit — agent-trust-hub — ios-app-development