geo-magazine-slides

Pass

Audited by Gen Agent Trust Hub on Nov 22, 2026

Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
  • [SAFE]: No malicious patterns or security vulnerabilities were detected. The instructions are focused on visual styling and content organization within the agent's internal environment. The explicit prohibition of external image downloads (Step 4) mitigates risks associated with remote resource fetching.
  • [INDIRECT_PROMPT_INJECTION]: The skill defines a process for ingesting user-provided data to generate presentations. This represents a typical functional ingestion surface rather than an exploitable vulnerability. 1. Ingestion points: SKILL.md (Step 1: Gather Content Requirements). 2. Boundary markers: None specified. 3. Capability inventory: PPTX file creation. 4. Sanitization: None specified.
Audit Metadata
Risk Level
SAFE
Analyzed
Nov 22, 2026, 01:11 AM