alterlab-vcd-infographic
Pass
Audited by Gen Agent Trust Hub on Apr 5, 2026
Risk Level: SAFE
Full Analysis
- [SAFE]: No security issues detected. The skill's operations, including reading datasets and writing design specifications, are consistent with its stated purpose as an information design assistant.
- [PROMPT_INJECTION]: Evaluated for indirect prompt injection surface. 1. Ingestion points: Reads user-provided datasets, research reports, and project files (SKILL.md). 2. Boundary markers: No specific delimiters are mentioned in the instructions. 3. Capability inventory: Web search, file reading, and file system write access (SKILL.md). 4. Sanitization: Relies on standard agent guardrails and no specific filtering is described. This attack surface is considered a standard and low-risk inherent property of the skill's intended data-processing function.
Audit Metadata