ai-startup-advisor

Pass

Audited by Gen Agent Trust Hub on Mar 24, 2026

Risk Level: SAFEPROMPT_INJECTION
Full Analysis
  • [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection because it processes untrusted user-provided ideas and external data from WebSearch/WebFetch tools without boundary markers or input sanitization, while having access to high-privilege tools.
  • Ingestion points: Startup idea descriptions in SKILL.md and web content retrieved via WebFetch/WebSearch.
  • Boundary markers: No delimiters or isolation instructions are present to distinguish user data from the core strategic logic.
  • Capability inventory: Includes Bash, Write, and Edit tool permissions which could be exploited if an injection occurs.
  • Sanitization: No sanitization or filtering of external input is performed before processing.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 24, 2026, 11:17 AM
Security Audit — agent-trust-hub — ai-startup-advisor