idea-validator
Pass
Audited by Gen Agent Trust Hub on Apr 12, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill contains an indirect prompt injection surface through the interpolation of user-supplied business ideas into research agent prompts.\n- Ingestion points: Business ideas, pitches, and plans provided by the user in Phase 1 (SKILL.md).\n- Boundary markers: No explicit delimiters (like tags) or instructions to ignore embedded commands are present in the research briefs defined in Phase 4 (SKILL.md).\n- Capability inventory: The skill spawns sub-agents (Agent tool) and conducts web research (WebSearch) in Phase 4.\n- Sanitization: The skill lacks input sanitization or filtering to prevent malicious instructions within the user-provided idea from influencing the sub-agents.
Audit Metadata