command-audit-rn

Pass

Audited by Gen Agent Trust Hub on Aug 5, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is subject to indirect prompt injection risks as it processes untrusted data from user codebases during the audit workflow.
  • Ingestion points: Expo project codebase (SKILL.md).
  • Boundary markers: Absent; the skill does not explicitly use delimiters to isolate code content from instructions.
  • Capability inventory: Spawning specialized sub-agents and executing audit-specific skills (SKILL.md).
  • Sanitization: No evidence of data sanitization or instruction filtering before processing codebase contents.
Audit Metadata
Risk Level
SAFE
Analyzed
Aug 5, 2026, 11:17 PM
Security Audit — agent-trust-hub — command-audit-rn