systems-thinking
Pass
Audited by Gen Agent Trust Hub on Apr 11, 2026
Risk Level: SAFEPROMPT_INJECTION
Full Analysis
- [PROMPT_INJECTION]: The skill exhibits a surface for indirect prompt injection via its research and analysis process.\n
- Ingestion points: User-defined topics and web search results obtained during the context research phase in SKILL.md.\n
- Boundary markers: Absent; the instructions do not define delimiters to separate external untrusted data from the analysis framework.\n
- Capability inventory: Web search, text generation, and Mermaid diagram generation.\n
- Sanitization: Absent; no methods for validating or filtering external content are described.
Audit Metadata