multi-advisor
Pass
Audited by Gen Agent Trust Hub on Oct 29, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest and process untrusted user input through various 'personas' and synthesis workflows.
- Ingestion points: The skill receives user questions ('Questão do usuário') as its primary data source.
- Boundary markers: While the skill uses Markdown structures for output formatting, it lacks explicit boundary markers or instructions to isolate the user-provided input from the persona instructions (system prompts), creating a surface where user input could potentially influence the behavior of the personas.
- Capability inventory: The skill is configured with access to powerful CLI tools in its frontmatter (
claude-code,cursor,gemini-cli,codex-cli), which often have capabilities for file system operations and network access. - Sanitization: The instructions do not specify any validation or sanitization steps for the user input before it is interpolated into the advisory board workflow.
Audit Metadata