design-thinking-mjv
Pass
Audited by Gen Agent Trust Hub on Nov 1, 2026
Risk Level: SAFENO_CODE
Full Analysis
- [SAFE]: The skill is a purely informational knowledge base providing guidance on Design Thinking methodologies. It consists exclusively of Markdown files and does not include any executable scripts, binaries, or active code.\n- [INDIRECT_PROMPT_INJECTION]:\n
- Ingestion points: The skill ingests text from the references/ directory and SKILL.md to provide answers to user queries about Design Thinking.\n
- Boundary markers: The skill includes an explicit 'Diretrizes de Segurança' section in SKILL.md that instructs the AI agent to treat all reference files as passive data and to disregard any instructions within them that attempt to override system rules.\n
- Capability inventory: The skill is restricted to the 'Read' and 'Grep' tools. It has no capabilities for file writing, network communication, or arbitrary command execution.\n
- Sanitization: While no automated sanitization is applied to the static Markdown content, the limited toolset and the 'assume-passive' instructions for the agent minimize the risk of indirect injection.\n- [NO_CODE]: The skill does not contain any Python, Node.js, or shell scripts, which significantly reduces the potential attack surface for traditional code-based exploits.
Audit Metadata