infographics

Pass

Audited by Gen Agent Trust Hub on Mar 15, 2026

Risk Level: SAFEPROMPT_INJECTIONEXTERNAL_DOWNLOADS
Full Analysis
  • [PROMPT_INJECTION]: The skill is vulnerable to indirect prompt injection because it processes user-supplied text to generate infographics. Ingestion points: User input provided via the prompt argument in scripts/generate_infographic.py is utilized throughout the generation and research phases. Boundary markers: Absent. User input is interpolated directly into system instructions within scripts/generate_infographic_ai.py without protective delimiters or constraints. Capability inventory: The skill utilizes network access (requests.post), subprocess execution (subprocess.run), and filesystem operations (Path.write_bytes). Sanitization: Absent. No validation or escaping is applied to user strings before they are incorporated into model prompts.
  • [EXTERNAL_DOWNLOADS]: The skill communicates with the OpenRouter API (openrouter.ai) and Perplexity (via OpenRouter) to perform research and generate images. These are recognized services essential to the skill's operation.
Audit Metadata
Risk Level
SAFE
Analyzed
Mar 15, 2026, 11:46 AM