rtl

Pass

Audited by Gen Agent Trust Hub on Aug 15, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [SAFE]: The skill is entirely instructional, providing best practices for React Native RTL support (e.g., using logical properties like marginStart instead of marginLeft).
  • [SAFE]: No network exfiltration, hardcoded credentials, or suspicious remote code patterns were identified.
  • [SAFE]: The skill references internal project files and standard library components consistent with its stated purpose.
  • [INDIRECT_PROMPT_INJECTION]: The skill asks the agent to audit user-provided code diffs, which represents a surface for indirect prompt injection if the analyzed content contains malicious instructions.
  • Ingestion points: External code diffs and named project files (SKILL.md).
  • Boundary markers: Absent; no specific delimiters or instructions to ignore embedded commands within the audited code are provided.
  • Capability inventory: Read access to source files and generation of audit findings; no high-privilege execution is defined.
  • Sanitization: Absent; no input validation or filtering is specified for the ingested content.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 15, 2026, 12:55 PM
Security Audit — agent-trust-hub — rtl