alterlab-nmc-portfolio-curator
Pass
Audited by Gen Agent Trust Hub on Sep 22, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to ingest untrusted data from external sources, creating a potential vector for indirect prompt injection attacks. \n- Ingestion points: The 'Audit & Inventory' and 'Research first' protocols specify that the agent should read existing project files (briefs, work samples, drafts) and search the web for industry standards and benchmarks. \n- Boundary markers: The instructions do not define clear delimiters or system-level directives to isolate these inputs or ignore any natural language instructions contained within them. \n- Capability inventory: The agent has the capability to write multiple markdown files to the project directory, including portfolio plans, descriptions, and bio sets. \n- Sanitization: There is no evidence of content sanitization, validation, or escaping logic applied to the external data before it is processed and incorporated into generated deliverables.
Audit Metadata