strategy-planner
Pass
Audited by Gen Agent Trust Hub on Apr 13, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill is susceptible to indirect prompt injection due to its core functionality of analyzing untrusted external data. \n- Ingestion points: Processes user-uploaded files for SWOT analysis and fetches corporate filings from the DART (Electronic Disclosure System) via MCP tools in SKILL.md and references/startup-launcher.md. \n- Boundary markers: The instructions lack explicit delimiters or "ignore instructions" markers to separate the analyzed data from the agent's core operational logic. \n- Capability inventory: The skill utilizes complex reasoning (sequential thinking), file format conversion (via moai-office), and content generation (via moai-marketing). \n- Sanitization: There is no evidence of content sanitization or validation for the inputs received from user files or external API responses.
Audit Metadata